© 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. 20-CLT-HP
    7. 72269
    Prev
    Next
    INDEX
    Explanations

    technical / code language snippets

    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
     externi
    -0.59
     pstmt
    -0.54
     catalana
    -0.53
     Hearts
    -0.52
     hearts
    -0.50
    adaptiveStyles
    -0.50
     ligiloj
    -0.50
    HasBeenSet
    -0.49
    NSYLVANIA
    -0.49
    Personensuche
    -0.49
    POSITIVE LOGITS
    ScopeManager
    0.58
    fromnode
    0.50
    enumi
    0.50
    reportError
    0.49
     GetEnumerator
    0.49
    وعة
    0.49
    enterOuterAlt
    0.49
    MetaObject
    0.47
    makeConstraints
    0.47
     تانيه
    0.47
    Activations Density 0.001%

    No Known Activations