© 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. 20-CLT-HP
    7. 77720
    Prev
    Next
    INDEX
    Explanations

    tropical

    np_max-act-logits · 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
     Quince
    -0.57
     CanadaChoose
    -0.55
    pfel
    -0.53
    ingers
    -0.52
     Ahl
    -0.50
     Schenk
    -0.50
    acar
    -0.50
    wachs
    -0.49
    JsonInclude
    -0.48
    Builders
    -0.48
    POSITIVE LOGITS
     MonoBehaviour
    0.62
    UrlResolution
    0.59
     مشين
    0.58
    makeText
    0.54
    storm
    0.54
    findpost
    0.52
    IsContent
    0.50
    SharedDtor
    0.50
     oprot
    0.50
    strix
    0.49
    Activations Density 0.000%

    No Known Activations