Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 919
    Prev
    Next
    INDEX
    Explanations

    period token

    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
    ↵↵
    -0.97
     The
    -0.96
     This
    -0.88
     In
    -0.86
     It
    -0.85
     You
    -0.85
     There
    -0.84
     But
    -0.79
     As
    -0.78
     While
    -0.77
    POSITIVE LOGITS
    sub
    0.46
    c
    0.44
    id
    0.43
    vlád
    0.43
    set
    0.43
    do
    0.42
    or
    0.42
    his
    0.41
    x
    0.41
     partij
    0.41
    Activations Density 1.351%

    No Known Activations