© 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. 12124
    Prev
    Next
    INDEX
    Explanations

    Nature descriptions

    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
    SequentialGroup
    -0.56
     BoxFit
    -0.48
     للاسماء
    -0.48
     linkovi
    -0.45
    ::_('
    -0.44
     Coaster
    -0.44
    maten
    -0.42
    ardized
    -0.42
     تضيفلها
    -0.41
    TagMode
    -0.41
    POSITIVE LOGITS
    HasAnnotation
    0.64
     Emp
    0.61
     EconPapers
    0.59
    intéress
    0.57
     Lid
    0.56
    AsUp
    0.55
    cara
    0.55
     krop
    0.52
     EMP
    0.52
     LE
    0.52
    Activations Density 0.078%

    No Known Activations