© 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. 42526
    Prev
    Next
    INDEX
    Explanations

    impact

    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
    impact
    -2.20
     impact
    -2.19
    Impact
    -2.02
     Impact
    -1.90
    IMPACT
    -1.59
     IMPACT
    -1.58
     impacts
    -1.56
     impacting
    -1.56
     impacto
    -1.50
     impacted
    -1.30
    POSITIVE LOGITS
    ful
    0.78
    fully
    0.60
    ting
    0.60
     of
    0.57
    fulness
    0.56
    full
    0.56
    ing
    0.49
    ेड
    0.49
    fü
    0.47
    FUL
    0.46
    Activations Density 0.015%

    No Known Activations