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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12659
    Prev
    Next
    INDEX
    Explanations

    political and governmental references

    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
    227
    +0.14
    0.4%
    752
    +0.13
    0.4%
    1967
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2041
    +0.14
    0.06
    752
    +0.13
    0.04
    227
    +0.11
    0.05
    Negative Logits
     nutella
    -1.35
     intersper
    -1.25
     disagre
    -1.24
     shenan
    -1.22
     apprehen
    -1.18
     overcrow
    -1.17
     encomp
    -1.16
     ftre
    -1.13
     increa
    -1.13
     lmfao
    -1.12
    POSITIVE LOGITS
    thums
    0.63
    UnifiedTopology
    0.56
     Chambres
    0.56
     United
    0.55
    astify
    0.54
     Entre
    0.52
     Royaume
    0.52
    itanie
    0.52
     Bár
    0.52
    bó
    0.52
    Activations Density 0.258%

    No Known Activations