© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-RES-MATRYOSHKA-DC
    7. 1180
    Prev
    Next
    INDEX
    Explanations

    mentions of the hand or fingers

    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
     electroly
    -0.52
     NCERT
    -0.50
    Batis
    -0.48
     Fea
    -0.47
    ociação
    -0.47
    raszamy
    -0.46
     kite
    -0.44
     متعلقه
    -0.43
     strut
    -0.43
     Patro
    -0.43
    POSITIVE LOGITS
     hand
    2.36
     hands
    2.14
     Hand
    2.09
    Hand
    2.03
    hand
    1.98
     Hands
    1.95
     HAND
    1.91
    Hands
    1.87
    hands
    1.87
    HAND
    1.85
    Activations Density 0.591%

    No Known Activations