© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97238
    Prev
    Next
    INDEX
    Explanations

    effect

    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
    oredCriteria
    -0.70
    asyarakat
    -0.56
    parsedMessage
    -0.54
    RTEX
    -0.54
    ariable
    -0.53
     Dissent
    -0.52
    memoized
    -0.51
     ardından
    -0.50
     spake
    -0.49
     memoirs
    -0.49
    POSITIVE LOGITS
    ftagPool
    0.65
    ImageContext
    0.54
    AnchorStyles
    0.52
     intitulé
    0.51
     onCancelled
    0.49
    RectangleBorder
    0.48
     MainAxisSize
    0.48
     SqlCommand
    0.47
    ruptedException
    0.46
    
    0.46
    Activations Density 0.000%

    No Known Activations