© 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. 44216
    Prev
    Next
    INDEX
    Explanations

    akov

    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
    esez
    -0.69
     Moshe
    -0.63
     Shaksp
    -0.62
     wake
    -0.60
     Shakspeare
    -0.60
    
    -0.57
    ization
    -0.56
     beams
    -0.56
     doorway
    -0.56
     Pergamon
    -0.55
    POSITIVE LOGITS
    mybatisplus
    0.65
    styleType
    0.60
     mukaan
    0.58
    utenants
    0.53
    PARATUS
    0.51
    SharedCtor
    0.51
    pertory
    0.50
    OOTD
    0.50
    endphp
    0.48
    üedad
    0.48
    Activations Density 0.444%

    No Known Activations