© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 493
    Prev
    Next
    INDEX
    Explanations

    formal writing

    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
    ChildScrollView
    -0.71
    onViewCreated
    -0.68
    mergeFrom
    -0.66
    IsContent
    -0.65
     ujednoznacz
    -0.63
    providedIn
    -0.62
    ніципалі
    -0.60
    SourceChecksum
    -0.59
    ParallelGroup
    -0.59
    ViewImports
    -0.58
    POSITIVE LOGITS
     culturelles
    0.55
     missione
    0.54
     mourut
    0.53
     varme
    0.52
    3
    0.51
    5
    0.50
    2
    0.50
     jäsen
    0.49
     møte
    0.48
     nationaux
    0.48
    Activations Density 0.002%

    No Known Activations