© 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. 4-CLT-HP
    7. 4342
    Prev
    Next
    INDEX
    Explanations

    software licenses

    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
    GEBURTSDATUM
    -0.64
     חיצוניים
    -0.63
    jgl
    -0.62
    expandindo
    -0.58
     referenties
    -0.54
     numberWith
    -0.53
     通販
    -0.52
     shelves
    -0.52
    +#+#
    -0.52
     nawr
    -0.52
    POSITIVE LOGITS
     médicaux
    0.59
     judiciales
    0.53
     rédig
    0.53
     sonre
    0.52
     preuves
    0.51
     bené
    0.51
     Wade
    0.50
    มาณ
    0.50
     judiciaire
    0.50
     Sue
    0.49
    Activations Density 0.003%

    No Known Activations