© 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. 958
    Prev
    Next
    INDEX
    Explanations

    entitled/titled

    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
    dafx
    -0.47
    We
    -0.47
    Aiheesta
    -0.47
     externi
    -0.46
     clin
    -0.46
    medriver
    -0.45
    Developed
    -0.45
    Clin
    -0.44
    weile
    -0.44
    This
    -0.43
    POSITIVE LOGITS
     InputDecoration
    0.60
     متعلقه
    0.59
    ichtig
    0.54
    Demikian
    0.52
     للاسماء
    0.50
     $"{
    0.50
    <>("
    0.50
    حياته
    0.50
    }))
    0.50
     EXAMIN
    0.49
    Activations Density 0.001%

    No Known Activations