© 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. 0-CLT-HP
    7. 42786
    Prev
    Next
    INDEX
    Explanations

    of

    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
     to
    -0.96
     by
    -0.49
     passing
    -0.44
    segno
    -0.42
     on
    -0.41
    aldas
    -0.41
    PSO
    -0.41
     тобой
    -0.40
    InputBorder
    -0.40
     in
    -0.39
    POSITIVE LOGITS
    parsedMessage
    0.89
    CodedInputStream
    0.83
    SharedDtor
    0.82
     anſ
    0.81
     noqa
    0.76
     uſe
    0.74
    addCriterion
    0.71
     eſ
    0.71
     незавершена
    0.71
     $_"
    0.70
    Activations Density 0.008%

    No Known Activations