© 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. 5-CLT-HP
    7. 92668
    Prev
    Next
    INDEX
    Explanations

    genic

    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
    ArgsConstructor
    -0.59
    AutoScale
    -0.58
    Gib
    -0.55
    ernas
    -0.54
    ↵
    -0.54
     Mas
    -0.53
     CanadaChoose
    -0.53
     ge
    -0.53
     San
    -0.52
    bitur
    -0.52
    POSITIVE LOGITS
     snippetHide
    0.56
     myſelf
    0.53
    )++;
    0.52
     Monfieur
    0.50
     optimise
    0.50
     fieldNum
    0.50
    zwischen
    0.47
     raiſ
    0.47
    UrlResolution
    0.47
     help
    0.46
    Activations Density 0.049%

    No Known Activations