© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 1075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     насељу
    -0.65
     passphrase
    -0.55
     strikes
    -0.54
     iyon
    -0.52
    IndentedString
    -0.49
     Strikes
    -0.48
    GIVEREF
    -0.48
    seteq
    -0.47
    ごめんなさい
    -0.47
    すみません
    -0.47
    POSITIVE LOGITS
     surla
    0.49
    WebElementEntity
    0.45
     crossorigin
    0.45
     nå
    0.45
    insee
    0.44
     aub
    0.43
     ModelExpression
    0.43
    Теперь
    0.42
     Citroen
    0.42
     IPX
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.