© 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. 20-CLT-HP
    7. 72837
    Prev
    Next
    INDEX
    Explanations

    hand

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.59
    cplusplus
    -0.54
     <",
    -0.52
    findpost
    -0.51
    cstdio
    -0.51
    XmlAccessType
    -0.48
    SceneManagement
    -0.47
    FetchType
    -0.47
    cz
    -0.46
     cellspacing
    -0.46
    POSITIVE LOGITS
    hand
    0.66
    HAND
    0.65
    hands
    0.63
    drug
    0.58
     hands
    0.58
    dose
    0.57
     AssemblyCulture
    0.54
    Hands
    0.54
    aid
    0.53
     Hands
    0.53
    Activations Density 0.000%

    No Known Activations