© 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. 20-CLT-HP
    7. 75489
    Prev
    Next
    INDEX
    Explanations

    source

    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
    protoimpl
    -0.70
     bribery
    -0.69
     intimidation
    -0.66
     abusive
    -0.65
     oppressive
    -0.64
     corrupted
    -0.64
     falla
    -0.63
     deceitful
    -0.62
     deceptive
    -0.62
     sinister
    -0.61
    POSITIVE LOGITS
    tvguidetime
    0.58
     الدولى
    0.54
    makeText
    0.53
    didSet
    0.48
     StatefulWidget
    0.43
    otriz
    0.42
    RectangleBorder
    0.42
     ModelExpression
    0.42
    หวัด
    0.42
    glad
    0.41
    Activations Density 0.000%

    No Known Activations