Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73805
    Prev
    Next
    INDEX
    Explanations

    Non-standard text and code

    np_max-act-logits · 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
    IntoConstraints
    -0.48
     }{@
    -0.48
     hereto
    -0.48
    Permalink
    -0.48
     ●
    -0.45
    setVerticalGroup
    -0.45
    nonatomic
    -0.44
    الإنجليزية
    -0.44
     ```
    -0.44
    -​
    -0.44
    POSITIVE LOGITS
    usitis
    0.63
     للمعارف
    0.60
    ropractor
    0.59
     للاسماء
    0.58
    strij
    0.57
     Moriarty
    0.57
     rq
    0.57
    rungsseite
    0.57
    NES
    0.57
    StackNavigator
    0.56
    Activations Density 0.002%

    No Known Activations