© 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. 1-CLT-HP
    7. 13076
    Prev
    Next
    INDEX
    Explanations

    summary

    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
    
    -0.63
    dymyr
    -0.56
     שוליים
    -0.53
    doctype
    -0.53
    ⓧ
    -0.52
    TextEditing
    -0.50
    osoma
    -0.50
    amethasone
    -0.50
    alline
    -0.49
    perative
    -0.49
    POSITIVE LOGITS
    ibatis
    0.76
    MigrationBuilder
    0.65
    ftagPool
    0.62
    ContentAsync
    0.61
     barnen
    0.61
     emperador
    0.58
     élas
    0.56
     ChromeDriver
    0.56
    XmlRootElement
    0.54
     AssemblyVersion
    0.53
    Activations Density 0.176%

    No Known Activations