© 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. 1-CLT-HP
    7. 10232
    Prev
    Next
    INDEX
    Explanations

    modal verbs

    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
     will
    -0.79
     would
    -0.79
    would
    -0.61
     to
    -0.60
     and
    -0.59
     may
    -0.58
    will
    -0.54
     could
    -0.50
     can
    -0.50
     sẽ
    -0.50
    POSITIVE LOGITS
     houſe
    0.76
     Monfieur
    0.73
     ſtate
    0.71
     Jefus
    0.71
     BoxDecoration
    0.71
     Efq
    0.71
     Houſe
    0.69
     auffi
    0.67
     Económica
    0.65
     Agamemnon
    0.65
    Activations Density 0.089%

    No Known Activations