© 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. 1081
    Prev
    Next
    INDEX
    Explanations

    intervention

    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
    CPtr
    -0.56
    PropertyChanging
    -0.54
    }\]
    -0.54
    gnore
    -0.52
     disambiguazione
    -0.52
    Lur
    -0.51
    WithEmail
    -0.49
     requestCode
    -0.49
     lenker
    -0.49
    曖昧さ回避
    -0.48
    POSITIVE LOGITS
     programs
    0.68
     into
    0.67
     programmes
    0.65
     against
    0.63
     strategies
    0.63
     to
    0.62
     studies
    0.61
    sprogram
    0.59
    maßnahmen
    0.57
     aimed
    0.54
    Activations Density 0.001%

    No Known Activations