© 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. 22-RES-MATRYOSHKA-DC
    7. 2664
    Prev
    Next
    INDEX
    Explanations

    mathematical equations or expressions

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.22.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.22.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
    évaluateur
    -0.81
    Демографія
    -0.78
    󠁴
    -0.76
    GEBURTSDATUM
    -0.73
    MigrationBuilder
    -0.72
    ----</
    -0.71
     سكانية
    -0.68
     &___
    -0.68
    igslist
    -0.66
    parsedMessage
    -0.66
    POSITIVE LOGITS
     الاطلاع
    0.59
     }{
    0.58
    IMPORTED
    0.54
    Buongiorno
    0.49
    -(
    0.49
    rú
    0.49
    *}{
    0.48
    partial
    0.47
    dX
    0.46
    ∂
    0.46
    Activations Density 0.075%

    No Known Activations