© 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. 2867
    Prev
    Next
    INDEX
    Explanations

    mentions of time, location, or position

    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
    клопе
    -0.90
     مُعرِّف
    -0.83
     nahilalakip
    -0.81
    ']=='
    -0.78
    ']==
    -0.77
     snippetHide
    -0.77
    brainly
    -0.75
    것은
    -0.73
     Theſe
    -0.72
    Izvori
    -0.72
    POSITIVE LOGITS
    .
    0.83
     but
    0.74
    ;
    0.59
     (
    0.57
     because
    0.54
     ("
    0.50
     where
    0.50
     or
    0.49
     (“
    0.48
    ,
    0.48
    Activations Density 0.526%

    No Known Activations