© 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. 92072
    Prev
    Next
    INDEX
    Explanations

    Mad

    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
    arine
    -0.63
     يتيمه
    -0.62
    íncia
    -0.59
    getColumnIndex
    -0.59
    hode
    -0.57
    lencia
    -0.56
     codon
    -0.56
     Poy
    -0.55
    iph
    -0.54
    InjectAttribute
    -0.54
    POSITIVE LOGITS
     ExecuteAsync
    0.53
     متعلقه
    0.52
    Искәрмәләр
    0.49
     ApiException
    0.47
     rubrique
    0.47
    esModule
    0.46
    Newswire
    0.45
     Turquie
    0.44
     mẽ
    0.44
    Jsp
    0.43
    Activations Density 0.254%

    No Known Activations