© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14431
    Prev
    Next
    INDEX
    Explanations

    classified information and terms related to classification levels within documents

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1742
    +0.16
    0.6%
    1870
    +0.13
    0.5%
    1624
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1742
    +0.16
    0.02
    680
    +0.13
    0.01
    1624
    +0.12
    0.01
    Negative Logits
     superintend
    -0.61
    madeus
    -0.59
    Allister
    -0.58
     oleo
    -0.56
     antem
    -0.56
    nemia
    -0.54
     mercu
    -0.54
     abat
    -0.53
    Tracce
    -0.53
     venezuela
    -0.52
    POSITIVE LOGITS
     classification
    1.37
     classified
    1.29
     Classification
    1.21
     classify
    1.19
    classified
    1.18
     classifications
    1.17
    Classification
    1.16
    classification
    1.15
    classify
    1.11
     classifier
    1.08
    Activations Density 0.065%

    No Known Activations