© 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. 4-CLT-HP
    7. 93
    Prev
    Next
    INDEX
    Explanations

    assistance or public service

    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
    tifkan
    -0.57
     benefit
    -0.46
     favor
    -0.45
    יסטור
    -0.44
    szön
    -0.43
     bénéficient
    -0.43
     important
    -0.41
     importantly
    -0.41
     wonderful
    -0.41
     useful
    -0.41
    POSITIVE LOGITS
    LookAnd
    0.79
    PerformLayout
    0.75
    UnknownFieldSet
    0.73
    protoimpl
    0.73
    новништво
    0.72
    ⓧ
    0.71
    RetentionPolicy
    0.69
    行政区划
    0.67
    expandindo
    0.65
    caris
    0.65
    Activations Density 0.002%

    No Known Activations