© 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. 96255
    Prev
    Next
    INDEX
    Explanations

    will

    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
     cellspacing
    -0.66
    بوابة
    -0.63
     disponibilités
    -0.58
    Diwedd
    -0.57
    Erreferentziak
    -0.57
    IBOutlet
    -0.57
    TestingModule
    -0.56
    Demografia
    -0.56
    onAttach
    -0.53
    ielles
    -0.53
    POSITIVE LOGITS
    rrggbb
    0.52
     utafitiHapana
    0.47
    handelt
    0.46
     viendra
    0.46
    pielt
    0.46
    出版年
    0.45
     noDo
    0.44
     bisogno
    0.43
     nästa
    0.43
    ThroughAttribute
    0.42
    Activations Density 0.002%

    No Known Activations