© 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. 20-CLT-HP
    7. 74971
    Prev
    Next
    INDEX
    Explanations

    code/data

    np_max-act-logits · 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
     considerable
    -0.89
     lots
    -0.84
     LOTS
    -0.79
     plenty
    -0.72
     amount
    -0.72
     amounts
    -0.71
     alot
    -0.70
     Considerable
    -0.70
     loads
    -0.67
    lots
    -0.67
    POSITIVE LOGITS
     ModelExpression
    0.85
    Personendaten
    0.68
    zarchiwizowane
    0.68
     CanadaChoose
    0.67
     HasFactory
    0.66
    -------------</
    0.65
    ImageContext
    0.65
    ubio
    0.63
    __*/
    0.63
     يتيمه
    0.63
    Activations Density 0.001%

    No Known Activations