© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1985
    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
    -2.17
     impact
    -2.14
    Impact
    -1.97
     Impact
    -1.89
     impacts
    -1.69
     impacted
    -1.68
     IMPACT
    -1.66
     impacting
    -1.63
    IMPACT
    -1.58
     impacto
    -1.53
    POSITIVE LOGITS
    ting
    0.52
    ty
    0.43
    turi
    0.43
     teg
    0.42
    te
    0.42
     hazard
    0.42
    ynthetic
    0.41
    alie
    0.40
     j
    0.39
     fra
    0.39
    Activations Density 0.365%

    No Known Activations