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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 8437
    Prev
    Next
    INDEX
    Explanations

    textual representations of data entries or values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setAge
    -0.54
    latego
    -0.50
    inescence
    -0.50
     démocratique
    -0.49
    bici
    -0.49
    Reason
    -0.48
    افع
    -0.47
     Dumas
    -0.47
    Agencies
    -0.46
     agencies
    -0.46
    POSITIVE LOGITS
    UnusedPrivate
    0.84
    bootstrapcdn
    0.77
    awtextra
    0.71
    GetAxis
    0.66
    WebServlet
    0.64
    <!--[
    0.63
    +:+
    0.62
    ingale
    0.62
    GraphicsUnit
    0.60
    getSystemService
    0.60
    Activations Density 0.008%

    No Known Activations