© 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. 13085
    Prev
    Next
    INDEX
    Explanations

    not

    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
    setVerticalGroup
    -0.59
    razos
    -0.59
    Poloha
    -0.56
     excelencia
    -0.55
    tholes
    -0.53
    typeorm
    -0.52
    cheron
    -0.52
     verschillen
    -0.52
    arankan
    -0.52
    RetentionPolicy
    -0.52
    POSITIVE LOGITS
     been
    0.75
    IUrlHelper
    0.68
    <bos>
    0.65
     חיצוניים
    0.65
     hard
    0.61
     just
    0.57
     undergone
    0.57
     that
    0.55
     like
    0.55
     gonna
    0.52
    Activations Density 0.046%

    No Known Activations