© 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. 4-CLT-HP
    7. 4524
    Prev
    Next
    INDEX
    Explanations

    years

    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
     الاطلاع
    -0.43
     inferiores
    -0.35
    idea
    -0.34
     AssemblyCulture
    -0.34
    labelledby
    -0.33
    iness
    -0.32
     recomienda
    -0.31
    тво
    -0.30
     ordeal
    -0.30
     económicos
    -0.30
    POSITIVE LOGITS
    
    0.77
     ✭✭
    0.76
    enterOuterAlt
    0.76
    PreferredItem
    0.73
    webElementXpaths
    0.72
     OFDb
    0.69
     Parcel
    0.69
    OGND
    0.68
     يتيمه
    0.68
     Audiodateien
    0.68
    Activations Density 0.019%

    No Known Activations