© 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. 1196
    Prev
    Next
    INDEX
    Explanations

    pharmacology/mechanical systems

    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
     feroit
    -0.76
     chré
    -0.75
     quelcon
    -0.69
     étoit
    -0.68
     auroit
    -0.68
     Paglinawan
    -0.68
     fût
    -0.67
     dévelo
    -0.66
     rapides
    -0.66
     scolaires
    -0.66
    POSITIVE LOGITS
    usermodel
    0.63
    y
    0.60
    d
    0.59
    ed
    0.57
    .
    0.57
    n
    0.57
     parad
    0.56
    ised
    0.54
    em
    0.54
    ized
    0.54
    Activations Density 0.057%

    No Known Activations