© 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
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96121
    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
    ⓧ
    -0.59
     nakalista
    -0.55
    WriteBarrier
    -0.54
    PreferredItem
    -0.52
     Toujours
    -0.51
     Sensitive
    -0.50
     ceci
    -0.49
    그
    -0.48
     Whatever
    -0.48
    WriteLiteral
    -0.47
    POSITIVE LOGITS
    utives
    0.55
    tizens
    0.53
    ITICAL
    0.52
    phobia
    0.52
    endpush
    0.51
    JScrollPane
    0.50
     tribune
    0.50
    erees
    0.49
     sherpa
    0.49
    leine
    0.48
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.