© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 13456
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to indexing in programming

    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
    316
    +0.19
    0.8%
    501
    +0.18
    0.7%
    204
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.19
    0.03
    501
    +0.18
    0.02
    900
    +0.13
    0.02
    Negative Logits
     makro
    -0.54
     mariana
    -0.52
    Molto
    -0.51
     Compt
    -0.50
     courriel
    -0.50
     Drapeau
    -0.50
    Allora
    -0.49
    GTCX
    -0.49
     Doktor
    -0.47
     antik
    -0.47
    POSITIVE LOGITS
     index
    1.40
     Index
    1.29
    Index
    1.24
    index
    1.24
     indexes
    1.20
     INDEX
    1.12
     indexing
    1.08
     indices
    1.08
    INDEX
    1.06
     getIndex
    1.06
    Activations Density 0.088%

    No Known Activations