© 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. 1989
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    <bos>
    -0.52
    them
    -0.50
    {}'.
    -0.48
    PackageInfo
    -0.48
     them
    -0.47
     spot
    -0.47
    Feature
    -0.46
    subscriber
    -0.46
    LookAnd
    -0.45
    quela
    -0.45
    POSITIVE LOGITS
     we
    1.22
    Datuak
    0.86
    providedIn
    0.85
    Portail
    0.74
     мы
    0.74
     تضيفلها
    0.73
     protoimpl
    0.73
     متعلقه
    0.72
     you
    0.71
     שוליים
    0.70
    Activations Density 0.007%

    No Known Activations