© 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. 2-RES-MATRYOSHKA-DC
    7. 4251
    Prev
    Next
    INDEX
    Explanations

    references to manual hand actions or activities involving hand use

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hands
    -1.50
     Handles
    -1.37
    hands
    -1.33
     HANDS
    -1.33
     handles
    -1.30
     Hands
    -1.30
    Hands
    -1.25
     fingers
    -1.21
     Handling
    -1.20
    handle
    -1.16
    POSITIVE LOGITS
     hand
    1.64
    Hand
    1.27
     Hand
    1.27
    hand
    1.01
     HAND
    0.87
     hånd
    0.60
    vscode
    0.50
     Ess
    0.50
     věci
    0.49
     slutt
    0.49
    Activations Density 0.022%

    No Known Activations