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. 5-CLT-HP
    4. 1538
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    astéro
    -0.56
    __).
    -0.53
    msgTypes
    -0.51
     LEP
    -0.50
    trise
    -0.49
    </thead>
    -0.49
    UnitTesting
    -0.49
    Fácil
    -0.49
    selaer
    -0.48
    ReusableCell
    -0.48
    POSITIVE LOGITS
     kaarangay
    0.66
     onOptions
    0.65
     foot
    0.63
    ResumeLayout
    0.63
     незавершена
    0.60
     StatelessWidget
    0.60
    SourceChecksum
    0.60
     FOOT
    0.56
    
    0.55
     MaterialApp
    0.54
    Activations Density 0.004%

    No Known Activations