© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 91156
    Prev
    Next
    INDEX
    Explanations

    Roles, responsibilities, functions

    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
    ⓧ
    -0.72
     mergeFrom
    -0.65
     noqa
    -0.65
    UpInside
    -0.65
    ---|---|
    -0.63
    readystatechange
    -0.59
    AutoScaleMode
    -0.57
     consultato
    -0.57
    туга
    -0.57
    DOCTYPE
    -0.56
    POSITIVE LOGITS
     Gaps
    0.53
    ✭✭
    0.51
     Nodes
    0.46
    ChildIndex
    0.46
    deck
    0.46
    OfWork
    0.46
     nodes
    0.46
     gaps
    0.46
     tabak
    0.44
     públicas
    0.43
    Activations Density 0.001%

    No Known Activations