© 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. 4-CLT-HP
    7. 4674
    Prev
    Next
    INDEX
    Explanations

    and

    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
     Degradation
    -0.65
     ſeveral
    -0.63
    degradation
    -0.63
     Reduction
    -0.63
    Reduction
    -0.62
    eced
    -0.62
     ModelExpression
    -0.61
     Elimination
    -0.58
    detectChanges
    -0.58
    setChecked
    -0.58
    POSITIVE LOGITS
     update
    0.63
     modernize
    0.52
     grow
    0.47
    UpdateCommand
    0.46
     complete
    0.46
    update
    0.45
     diversify
    0.44
    twimg
    0.44
     more
    0.43
     upgrade
    0.43
    Activations Density 0.002%

    No Known Activations