© 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. 1-CLT-HP
    7. 410
    Prev
    Next
    INDEX
    Explanations

    ron

    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
    ingale
    -1.28
    verdi
    -0.61
     autorytatywna
    -0.57
    Зноскі
    -0.53
    gimento
    -0.52
     تانيه
    -0.51
    PSL
    -0.50
    ingly
    -0.50
    rungsseite
    -0.49
    tanian
    -0.49
    POSITIVE LOGITS
    HtmlAttribute
    0.79
    EndContext
    0.66
    setVerticalGroup
    0.59
    IsContent
    0.59
    EDEFAULT
    0.58
    ErrUnexpectedEOF
    0.56
    epam
    0.56
     handleMessage
    0.54
    parsedMessage
    0.54
    
    0.51
    Activations Density 0.087%

    No Known Activations