© 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. 5-CLT-HP
    7. 91292
    Prev
    Next
    INDEX
    Explanations

    recommendations

    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
    RectangleBorder
    -0.60
    ISupport
    -0.54
     raiſ
    -0.54
     quæ
    -0.50
     habet
    -0.49
     noft
    -0.49
     greateſt
    -0.48
     deſt
    -0.47
     avoient
    -0.47
     ſtate
    -0.46
    POSITIVE LOGITS
     if
    0.73
     <>",
    0.66
    expandindo
    0.61
     дописавши
    0.60
    gebnis
    0.59
     Himo
    0.56
    nonatomic
    0.56
    XmlRootElement
    0.56
     even
    0.55
    AsUp
    0.55
    Activations Density 0.003%

    No Known Activations