© 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. 1-CLT-HP
    7. 13788
    Prev
    Next
    INDEX
    Explanations

    programming / technical code

    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
     Ramadan
    -0.71
    bah
    -0.69
    odrome
    -0.56
    neau
    -0.55
    UserScript
    -0.51
     onAnimation
    -0.45
     huid
    -0.44
    -
    -0.42
    numRows
    -0.41
    RTEX
    -0.40
    POSITIVE LOGITS
     autrement
    0.63
    mability
    0.60
    utoff
    0.58
    jspb
    0.57
    URCH
    0.57
    칭
    0.57
    mogen
    0.56
    !("{}",
    0.56
    iously
    0.55
     vôtre
    0.54
    Activations Density 0.009%

    No Known Activations