© 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. 97520
    Prev
    Next
    INDEX
    Explanations

    outcomes

    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
    zaki
    -0.57
    Disliked
    -0.54
    agascar
    -0.52
    subject
    -0.52
    alone
    -0.50
     résister
    -0.50
    withOpacity
    -0.50
     widespread
    -0.49
    tadora
    -0.49
     occhiali
    -0.49
    POSITIVE LOGITS
    RegressionTest
    0.82
     يتيمه
    0.82
    :✨
    0.81
    Билгалдахарш
    0.74
    SharedDtor
    0.74
     referrerpolicy
    0.71
    contentLoaded
    0.70
     dAtA
    0.69
    RenderAtEndOf
    0.69
    省市镇
    0.67
    Activations Density 1.544%

    No Known Activations