© 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. 97742
    Prev
    Next
    INDEX
    Explanations

    technical/scientific texts

    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
     brief
    -0.90
    قایناق‌لار
    -0.88
    createStatement
    -0.72
    brief
    -0.71
    RegistryLite
    -0.71
     Brief
    -0.70
     disambiguazione
    -0.68
    aarrggbb
    -0.66
    literals
    -0.65
     estekak
    -0.65
    POSITIVE LOGITS
    er
    0.63
     Celui
    0.59
    ApiModelProperty
    0.54
    ant
    0.53
    ness
    0.52
    ️
    0.52
    ergies
    0.50
    ள்ள
    0.49
    est
    0.48
    ing
    0.47
    Activations Density 0.794%

    No Known Activations