© 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. 2207
    Prev
    Next
    INDEX
    Explanations

    words that describe or predict something

    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
    ness
    -0.76
    ing
    -0.75
    nya
    -0.67
    er
    -0.66
    ers
    -0.63
    es
    -0.60
    nement
    -0.58
    ings
    -0.57
    ization
    -0.57
    IZATION
    -0.57
    POSITIVE LOGITS
     Efq
    0.94
     myſelf
    0.84
     ſeveral
    0.80
     Monfieur
    0.79
     Theſe
    0.75
    ViewImports
    0.75
    ."],
    0.73
     uſe
    0.72
     themſelves
    0.69
     juſ
    0.66
    Activations Density 0.376%

    No Known Activations