© 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. 1-CLT-HP
    7. 14409
    Prev
    Next
    INDEX
    Explanations

    coast

    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
    tvguidetime
    -0.84
    abestanden
    -0.70
    MessageTagHelper
    -0.69
    RuleContext
    -0.67
    oredCriteria
    -0.66
     lenker
    -0.66
    homonymie
    -0.66
    
    -0.62
    ArgsConstructor
    -0.62
    Espèce
    -0.60
    POSITIVE LOGITS
     stratégique
    0.60
     lepas
    0.49
    utenant
    0.49
     estratégico
    0.47
    Swatch
    0.47
    bootstrapcdn
    0.46
    فيات
    0.45
    frontmatter
    0.44
    ynen
    0.43
    hq
    0.42
    Activations Density 0.026%

    No Known Activations