© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 45792
    Prev
    Next
    INDEX
    Explanations

    fillings

    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
    ngdoc
    -0.53
     Mechanics
    -0.48
    pejo
    -0.45
    king
    -0.43
     voie
    -0.42
    inner
    -0.40
    choon
    -0.39
    TagMode
    -0.39
     indirect
    -0.38
    __':
    
    -0.38
    POSITIVE LOGITS
    KURZBESCHREIBUNG
    0.67
    قایناق‌لار
    0.61
    RenderAtEndOf
    0.59
    jmniej
    0.58
    Kjelder
    0.57
     gioca
    0.57
    expandindo
    0.57
     financières
    0.56
     humaines
    0.56
     Suprema
    0.56
    Activations Density 0.083%

    No Known Activations