© 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. 0-CLT-HP
    7. 93860
    Prev
    Next
    INDEX
    Explanations

    may

    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
    might
    -0.78
     may
    -0.76
     might
    -0.70
    may
    -0.63
     MIGHT
    -0.62
     Might
    -0.57
    maybe
    -0.57
     MAY
    -0.57
     zouden
    -0.57
    Might
    -0.56
    POSITIVE LOGITS
    <bos>
    0.98
    enumii
    0.80
    enumi
    0.80
     even
    0.74
    tagHelperRunner
    0.64
    GraphicsUnit
    0.62
     arşivlendi
    0.60
     be
    0.59
    SequentialGroup
    0.59
    SuppressLint
    0.58
    Activations Density 0.458%

    No Known Activations