© 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. 5503
    Prev
    Next
    INDEX
    Explanations

    is

    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
    ConstraintMaker
    -0.72
     Administrativna
    -0.68
     vermelhas
    -0.60
     frères
    -0.57
    PickerController
    -0.56
    xodo
    -0.56
    however
    -0.56
    ❋
    -0.55
    erializer
    -0.54
    /******/
    -0.53
    POSITIVE LOGITS
     الحره
    0.49
    windowFixed
    0.47
    nEnter
    0.46
    ProcessEvent
    0.46
    这是一
    0.45
     minor
    0.44
    ="?
    0.43
     meant
    0.43
     occasional
    0.43
    leyeb
    0.43
    Activations Density 0.000%

    No Known Activations