© 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. 91140
    Prev
    Next
    INDEX
    Explanations

    elling

    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
    DllImport
    -0.69
    complexContent
    -0.52
    ftagPool
    -0.52
    CreateMap
    -0.49
    下载附件
    -0.49
    UrlResolution
    -0.49
    ArgsConstructor
    -0.48
    ništ
    -0.48
    djangoproject
    -0.48
    internalType
    -0.47
    POSITIVE LOGITS
     the
    0.58
    mittags
    0.57
     Exp
    0.56
    =#{
    0.54
    ials
    0.51
    ilin
    0.51
     Attack
    0.50
     attack
    0.50
     Meilleures
    0.49
    iling
    0.49
    Activations Density 0.007%

    No Known Activations