© 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. 1142
    Prev
    Next
    INDEX
    Explanations

    3

    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
    KURZBESCHREIBUNG
    -0.81
     doubtnut
    -0.78
     Italijani
    -0.77
     HasFactory
    -0.72
     itſelf
    -0.72
    SEGUIR
    -0.71
     Forumite
    -0.70
     photolibrary
    -0.66
    \]
    -0.66
    bewerken
    -0.65
    POSITIVE LOGITS
    <eos>
    0.84
     _
    0.68
    ↵↵
    0.60
    ↵
    0.55
     .
    0.54
    ↵↵↵
    0.52
     @
    0.50
     I
    0.49
     <
    0.49
     {
    0.47
    Activations Density 0.000%

    No Known Activations