Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 12696
    Prev
    Next
    INDEX
    Explanations

    umatic

    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
    umatic
    -2.41
    Geplaatst
    -0.77
     وتسجيلات
    -0.66
    ScopeManager
    -0.64
    Chham
    -0.62
    Portail
    -0.62
    dicional
    -0.62
    Jeografia
    -0.61
    зулта
    -0.60
     chaînes
    -0.60
    POSITIVE LOGITS
    --
    0.46
     midway
    0.46
     interim
    0.45
     Schnitt
    0.43
    herin
    0.43
    Concern
    0.43
    '
    0.43
    ;
    0.42
     Camer
    0.42
     Belum
    0.42
    Activations Density 0.006%

    No Known Activations