© 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. 0-CLT-HP
    7. 91916
    Prev
    Next
    INDEX
    Explanations

    Nas

    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
     NAS
    -0.68
     Nas
    -0.58
    Nas
    -0.52
     nas
    -0.50
     scarlet
    -0.50
    s
    -0.48
     Horseshoe
    -0.47
     coron
    -0.47
    liferay
    -0.44
     Ciencias
    -0.42
    POSITIVE LOGITS
     متعلقه
    0.85
    OGND
    0.84
     فريبيس
    0.81
     tartalomajánló
    0.81
     мәкал
    0.76
    HtmlAttribute
    0.72
     initComponents
    0.68
    SourceChecksum
    0.68
     Normdatei
    0.65
    GEBURTS
    0.65
    Activations Density 0.488%

    No Known Activations