© 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
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 96263
    Prev
    Next
    INDEX
    Explanations

    violence and negative situations

    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
    ​—
    -0.69
     NSCoder
    -0.58
     yourself
    -0.57
     itſelf
    -0.56
     ſhe
    -0.54
    ſelf
    -0.54
     Houſe
    -0.53
    ſelves
    -0.53
     ſch
    -0.53
     XCTest
    -0.52
    POSITIVE LOGITS
     the
    0.73
    GOTREF
    0.57
    expandindo
    0.53
     @"/
    0.46
    zipped
    0.46
    ParallelGroup
    0.44
     onPostExecute
    0.44
    siella
    0.43
    InjectAttribute
    0.42
    ]));
    
    0.42
    Activations Density 0.001%

    No Known Activations