© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93190
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    matchCondition
    -0.60
     fufficient
    -0.59
    PDATE
    -0.56
     ModelExpression
    -0.56
    AddField
    -0.56
    Ỡ
    -0.55
    Hauptartikel
    -0.55
    Trọng
    -0.54
    TryGetValue
    -0.52
    Euer
    -0.52
    POSITIVE LOGITS
     July
    0.54
     June
    0.50
     April
    0.49
    Revenir
    0.48
     August
    0.47
     November
    0.47
     October
    0.47
     May
    0.47
     ©
    0.47
    InstanceState
    0.47
    Activations Density 0.023%

    No Known Activations