© 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. 1-CLT-HP
    7. 356
    Prev
    Next
    INDEX
    Explanations

    football

    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
    ix
    -0.39
    nungs
    -0.39
    ع
    -0.38
    otonic
    -0.38
    yeron
    -0.37
    ofy
    -0.37
    ea
    -0.37
    oft
    -0.36
    ukų
    -0.36
    ed
    -0.36
    POSITIVE LOGITS
    Autoritní
    0.89
     nakalista
    0.85
     Numerade
    0.81
    JspWriter
    0.75
     BoxFit
    0.72
    VIAF
    0.68
    InputBorder
    0.68
     lccn
    0.68
     iprot
    0.67
     surla
    0.67
    Activations Density 0.015%

    No Known Activations