© 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. 20-CLT-HP
    7. 74493
    Prev
    Next
    INDEX
    Explanations

    uncommon words

    np_max-act-logits · 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
    ValueStyle
    -0.86
    setVerticalGroup
    -0.84
     estekak
    -0.73
     @"/
    -0.71
    httphttps
    -0.69
    AndEndTag
    -0.68
    contentLoaded
    -0.68
    InjectAttribute
    -0.68
    TagMode
    -0.68
    didSet
    -0.67
    POSITIVE LOGITS
     ujednoznacz
    0.50
    hall
    0.45
    hast
    0.42
    hten
    0.42
     دیکھیے
    0.40
    crans
    0.40
    zini
    0.40
    zal
    0.39
    gines
    0.39
    jenje
    0.39
    Activations Density 0.008%

    No Known Activations