© 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. 45065
    Prev
    Next
    INDEX
    Explanations

    written records

    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
     referenties
    -0.91
     Transcript
    -0.76
    __':
    -0.71
     HasFactory
    -0.61
    \{\\
    -0.61
    __":
    -0.61
    tinyos
    -0.60
    Tembelea
    -0.59
    __*/
    -0.58
    __':
    -0.57
    POSITIVE LOGITS
     noDo
    0.58
    forName
    0.56
    WebApplication
    0.56
    министра
    0.53
    NamedQuery
    0.50
    SuppressLint
    0.50
     rê
    0.49
    getOriginal
    0.47
    žev
    0.47
    Bacter
    0.46
    Activations Density 0.317%

    No Known Activations