© 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. 97716
    Prev
    Next
    INDEX
    Explanations

    modifications/updates

    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
     تضيفلها
    -0.75
     autorytatywna
    -0.73
    ScopeManager
    -0.72
     revised
    -0.69
     disambiguazione
    -0.69
    ंदीखरीदारी
    -0.69
    الدراسه
    -0.68
     revision
    -0.66
    revision
    -0.66
     profondeur
    -0.65
    POSITIVE LOGITS
     understanding
    0.63
    Brainz
    0.62
     understandings
    0.56
     VizieR
    0.55
     Antarctica
    0.54
     Pythagoras
    0.53
     Taq
    0.53
     Mademoiselle
    0.53
     Nauk
    0.52
    ìm
    0.52
    Activations Density 1.564%

    No Known Activations