© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 13778
    Prev
    Next
    INDEX
    Explanations

    support

    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
     فريبيس
    -0.66
    hares
    -0.60
     مرئيه
    -0.60
    шру
    -0.59
    ValueStyle
    -0.59
    />";
    -0.59
    anmoins
    -0.59
    eliness
    -0.58
     soutenir
    -0.57
    lihood
    -0.56
    POSITIVE LOGITS
     for
    0.65
    hiki
    0.49
     of
    0.49
    mability
    0.47
    calidad
    0.46
    rawDesc
    0.44
    OutputType
    0.44
     Blatt
    0.43
     davon
    0.41
     Anschluss
    0.41
    Activations Density 0.065%

    No Known Activations