© 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. 39797
    Prev
    Next
    INDEX
    Explanations

    just

    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
     in
    -0.74
     a
    -0.72
     as
    -0.65
     is
    -0.64
     an
    -0.63
     the
    -0.60
     Ste
    -0.57
     another
    -0.55
     Co
    -0.55
     Sp
    -0.54
    POSITIVE LOGITS
     preſent
    0.82
     فريبيس
    0.74
     doubtnut
    0.72
    poptosis
    0.70
    bootstrapcdn
    0.70
    İstinadlar
    0.68
    Diwedd
    0.68
     ſtand
    0.68
     defire
    0.68
     purpoſe
    0.68
    Activations Density 0.091%

    No Known Activations