© 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. 1-CLT-HP
    4. 12254
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
    expandindo
    -0.75
     <=",
    -0.71
     ExecuteAsync
    -0.71
     transfieras
    -0.70
     оригіналу
    -0.69
    KURZBESCHREIBUNG
    -0.69
     мәкал
    -0.68
    ereço
    -0.68
     ―――――
    -0.67
     BoxFit
    -0.66
    POSITIVE LOGITS
    I
    0.75
    can
    0.72
    are
    0.71
    if
    0.71
    so
    0.70
    for
    0.68
    but
    0.65
    i
    0.64
    and
    0.63
    is
    0.60
    Activations Density 0.035%

    No Known Activations