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. 4-CLT-HP
    4. 4130
    Prev
    Next
    INDEX
    Explanations

    you

    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
     referenties
    -0.58
     '\\;'
    -0.55
     Италијани
    -0.54
     OMITBAD
    -0.50
     للتو
    -0.49
     newBuilder
    -0.48
    WithEmail
    -0.43
    </thead>
    -0.43
    ReusableCell
    -0.42
     essenziale
    -0.42
    POSITIVE LOGITS
     NSCoder
    0.63
    CppCodeGen
    0.58
     Мексичка
    0.57
     combineReducers
    0.56
    CompilerServices
    0.55
    ValueStyle
    0.55
    ANTLR
    0.53
    ishna
    0.53
    eneuve
    0.53
    EndContext
    0.52
    Activations Density 0.002%

    No Known Activations