© 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. 1034
    Prev
    Next
    INDEX
    Explanations

    ovich

    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
     MainAxisSize
    -0.42
     Inline
    -0.40
     Mentions
    -0.40
    mapStateToProps
    -0.39
     Ambro
    -0.38
     snippetHide
    -0.36
     zobra
    -0.33
     CreateTagHelper
    -0.33
     Mentioned
    -0.33
     Exclu
    -0.32
    POSITIVE LOGITS
    はじめに
    0.75
    EDEFAULT
    0.69
    ovina
    0.66
    Personensuche
    0.66
    SourceChecksum
    0.65
     المعيارى
    0.64
    انيف
    0.64
    mnop
    0.62
    estris
    0.61
     Sprache
    0.61
    Activations Density 0.004%

    No Known Activations