© 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. 45204
    Prev
    Next
    INDEX
    Explanations

    names and code

    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
    s
    -0.70
    ی
    -0.69
    er
    -0.68
    EP
    -0.66
    y
    -0.66
     EP
    -0.64
    י
    -0.62
    WebVitals
    -0.59
    yaz
    -0.58
    yla
    -0.57
    POSITIVE LOGITS
     médicaux
    0.66
    🏼
    0.63
    InjectAttribute
    0.61
     lumineuse
    0.56
    namental
    0.53
     médicas
    0.53
     juridiques
    0.53
     parseFrom
    0.51
    Rohy
    0.50
     dramatist
    0.50
    Activations Density 0.907%

    No Known Activations