© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 90968
    Prev
    Next
    INDEX
    Explanations

    Actions performed

    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
     a
    -0.68
     the
    -0.66
     an
    -0.66
     takes
    -0.61
     its
    -0.60
     has
    -0.57
     is
    -0.55
     sends
    -0.55
     some
    -0.54
     ‘
    -0.53
    POSITIVE LOGITS
     noastre
    0.75
     myſelf
    0.70
     löyty
    0.67
     tarko
    0.67
     jotka
    0.66
     raiſ
    0.66
     themſelves
    0.64
     célèbres
    0.63
     sää
    0.63
     Cæsar
    0.62
    Activations Density 0.100%

    No Known Activations