© 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. 98123
    Prev
    Next
    INDEX
    Explanations

    the

    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
    HtmlAttribute
    -0.76
    UrlResolution
    -0.70
    __':
    -0.62
     pleaſure
    -0.62
     Jefus
    -0.61
     reaſon
    -0.59
    abetes
    -0.59
    Identyfik
    -0.58
    __":
    -0.58
    leyball
    -0.57
    POSITIVE LOGITS
    Personensuche
    0.70
    NameInMap
    0.48
     nuages
    0.46
     lèvres
    0.45
     tué
    0.45
     Krim
    0.43
     ProtoMessage
    0.42
     constaté
    0.42
     quitté
    0.41
     amnio
    0.41
    Activations Density 0.007%

    No Known Activations