© 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. 2043
    Prev
    Next
    INDEX
    Explanations

    programming or medical

    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
    الإنجليزية
    -0.68
    sidemargin
    -0.65
     kasarigan
    -0.64
    LEncoder
    -0.63
    -------------</
    -0.62
    StructField
    -0.61
     getSystem
    -0.61
    كويكب
    -0.60
     BoxFit
    -0.60
    BeginContext
    -0.59
    POSITIVE LOGITS
     sign
    0.90
     indication
    0.63
    sign
    0.60
    Sign
    0.60
    サイン
    0.59
     indicator
    0.57
     Sign
    0.57
     signs
    0.54
     INDIC
    0.53
    ंदीखरीदारी
    0.53
    Activations Density 0.000%

    No Known Activations