© 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. 1214
    Prev
    Next
    INDEX
    Explanations

    negative language

    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
    __':
    -0.89
    adaptiveStyles
    -0.88
    TypedDataSet
    -0.87
     thermoc
    -0.85
     mauvaises
    -0.84
    QMetaType
    -0.84
    featureID
    -0.83
    MigrationBuilder
    -0.81
    клопе
    -0.80
     AssemblyCulture
    -0.80
    POSITIVE LOGITS
     het
    0.57
     l
    0.57
     din
    0.56
     del
    0.54
     amb
    0.54
     ges
    0.53
     long
    0.52
     lo
    0.51
     je
    0.51
     best
    0.51
    Activations Density 0.092%

    No Known Activations