© 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. 96229
    Prev
    Next
    INDEX
    Explanations

    Negative sentiment

    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
     katkıda
    -0.42
    روج
    -0.41
    روف
    -0.41
    IEV
    -0.41
     enough
    -0.40
    gled
    -0.40
     span
    -0.39
     colored
    -0.39
     canon
    -0.39
    ="+
    -0.39
    POSITIVE LOGITS
    featureID
    0.89
    IntoConstraints
    0.88
     or
    0.88
    ClientSize
    0.84
     ExecuteAsync
    0.83
     InputDecoration
    0.81
    styleType
    0.79
     Wiktionnaire
    0.78
     مشين
    0.76
     חיצוניים
    0.76
    Activations Density 0.002%

    No Known Activations