© 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. 1-CLT-HP
    7. 15241
    Prev
    Next
    INDEX
    Explanations

    quotes

    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
     HasFactory
    -0.76
     Roskov
    -0.72
     onOptions
    -0.66
    MemoryWarning
    -0.64
    windowFixed
    -0.63
    PreferredItem
    -0.62
    ValueStyle
    -0.61
    VersionUID
    -0.60
     Ababa
    -0.57
     Reuters
    -0.57
    POSITIVE LOGITS
    ,
    0.93
    .
    0.84
    -
    0.74
    0.73
    )
    0.59
    :
    0.56
    ),
    0.54
     encima
    0.51
    )।
    0.50
    /
    0.49
    Activations Density 0.041%
    No Known Activations