© 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. 91173
    Prev
    Next
    INDEX
    Explanations

    Factual language

    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
    NameInMap
    -0.82
    SequentialGroup
    -0.69
    GOTREF
    -0.69
     tartalomajánló
    -0.69
    AndEndTag
    -0.68
    RenderAtEndOf
    -0.66
    XmlAccessorType
    -0.63
    ukone
    -0.62
     referenties
    -0.60
     HasFactory
    -0.57
    POSITIVE LOGITS
    TagMode
    0.52
    CppCodeGen
    0.50
     onCancelled
    0.49
    ft
    0.47
    Intent
    0.47
    elesai
    0.46
     valmist
    0.46
    Portály
    0.45
     klart
    0.45
    ISupport
    0.45
    Activations Density 0.076%

    No Known Activations