© 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. 0-CLT-HP
    7. 40000
    Prev
    Next
    INDEX
    Explanations

    common names

    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
     endless
    -0.63
    rocks
    -0.63
     Doe
    -0.56
    endless
    -0.53
    pilot
    -0.48
    nought
    -0.47
    /**
    -0.47
    ondo
    -0.46
     unending
    -0.44
    OUS
    -0.44
    POSITIVE LOGITS
    XmlAccessType
    0.78
    DoubleQuotes
    0.74
    MemoryWarning
    0.68
    setVerticalGroup
    0.67
     nahilalakip
    0.63
     ComVisible
    0.61
    SharedCtor
    0.61
    SequentialGroup
    0.60
    Népesség
    0.60
     ویکی‌پدی
    0.59
    Activations Density 0.055%

    No Known Activations