© 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. 5-CLT-HP
    7. 91834
    Prev
    Next
    INDEX
    Explanations

    int

    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
    ScopeManager
    -0.60
    +:+
    -0.57
    onAttach
    -0.56
    ật
    -0.55
    AnchorStyles
    -0.54
    BASELINE
    -0.54
    UIControlState
    -0.52
    enumi
    -0.51
     sánh
    -0.49
    IZABETH
    -0.48
    POSITIVE LOGITS
     caused
    0.60
     otherwise
    0.56
     characterized
    0.56
     refers
    0.54
     also
    0.54
     known
    0.53
     often
    0.53
    éhez
    0.52
     formerly
    0.52
     usually
    0.52
    Activations Density 0.000%

    No Known Activations