© 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. 5-CLT-HP
    7. 96270
    Prev
    Next
    INDEX
    Explanations

    1

    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
     Description
    -0.54
     description
    -0.49
    Sep
    -0.47
    </thead>
    -0.47
     Statisti
    -0.46
    合
    -0.44
    Description
    -0.44
    TV
    -0.43
     Color
    -0.43
    hasNext
    -0.43
    POSITIVE LOGITS
    WithIOException
    0.62
    awaiter
    0.57
    ContentAsync
    0.57
    addCriterion
    0.56
     >::
    0.56
    tableFuture
    0.56
     AssemblyVersion
    0.54
    Erstellt
    0.54
     الاطلاع
    0.53
    Hauptartikel
    0.52
    Activations Density 0.000%

    No Known Activations