© 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. 20-CLT-HP
    7. 74524
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act-logits · 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
    ContentAlignment
    -0.48
     Australian
    -0.47
     
    -0.46
     aluminum
    -0.45
     Canadian
    -0.45
     AppBundle
    -0.44
    WireFormat
    -0.44
    ouille
    -0.43
    -
    -0.42
     in
    -0.42
    POSITIVE LOGITS
    MigrationBuilder
    0.85
    #+#
    0.82
     uſe
    0.78
     contigo
    0.66
     fermés
    0.63
     myſelf
    0.62
    WebVitals
    0.62
     himſelf
    0.60
     beſt
    0.59
    دانشنامهٔ
    0.59
    Activations Density 0.001%

    No Known Activations