© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 72475
    Prev
    Next
    INDEX
    Explanations

    cycles and motorcycles

    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
    SequentialGroup
    -0.65
     MatDialog
    -0.63
     Normdatei
    -0.58
    DateTimeField
    -0.57
    Dichloroethane
    -0.57
     wireType
    -0.57
    ThroughAttribute
    -0.57
    extAlignment
    -0.56
    DockStyle
    -0.56
    setVerticalGroup
    -0.56
    POSITIVE LOGITS
     cycles
    1.04
     cycle
    1.00
    cycle
    0.88
    Cycle
    0.87
     bikes
    0.86
     Cycle
    0.86
    cycles
    0.86
     motorcycles
    0.85
     bike
    0.84
     motorcycle
    0.83
    Activations Density 0.004%

    No Known Activations