© 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. 1-CLT-HP
    7. 15227
    Prev
    Next
    INDEX
    Explanations

    hancing

    np_max-act · 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
    hancing
    -1.13
    iru
    -0.87
    ConstraintMaker
    -0.68
    urals
    -0.61
    曖昧さ回避
    -0.59
     betweenstory
    -0.57
     يتيمه
    -0.54
     complètes
    -0.53
    olphe
    -0.51
    ptonshire
    -0.51
    POSITIVE LOGITS
    rungsseite
    0.75
    JEE
    0.58
    vende
    0.58
    constraints
    0.56
     tabla
    0.54
    XIM
    0.51
    apen
    0.50
    Interop
    0.50
    قر
    0.48
    logging
    0.47
    Activations Density 0.003%

    No Known Activations