© 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. 5-CLT-HP
    7. 1953
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    }{*}{
    -0.41
    TC
    -0.41
    has
    -0.39
    ста
    -0.38
    она
    -0.36
     Malte
    -0.34
    のではなく
    -0.33
     Orgel
    -0.33
    restrial
    -0.32
     Jahrgang
    -0.31
    POSITIVE LOGITS
     ویکی‌پدیای
    0.91
     '\\;'
    0.79
    脚注の使い方
    0.79
     betweenstory
    0.78
     <=",
    0.77
    aarrggbb
    0.77
    <?
    0.77
    antMatchers
    0.77
     تكبرها
    0.75
    expandindo
    0.75
    Activations Density 0.093%

    No Known Activations