© 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. 20-CLT-HP
    7. 74756
    Prev
    Next
    INDEX
    Explanations

    flat

    np_max-act-logits · 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
    %)$
    -0.68
    makeConstraints
    -0.61
    kháu
    -0.57
    indd
    -0.54
    Демографія
    -0.54
    __*/
    -0.53
     dépens
    -0.52
     mourir
    -0.52
    twimg
    -0.52
    posedge
    -0.52
    POSITIVE LOGITS
    oredCriteria
    0.60
     يتيمه
    0.54
     propOrder
    0.53
     newOwner
    0.49
     coper
    0.48
     initComponents
    0.47
    poti
    0.46
    ThroughAttribute
    0.46
    irot
    0.45
    ViewImports
    0.45
    Activations Density 0.001%

    No Known Activations