© 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. 4-CLT-HP
    7. 327
    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
    teck
    -0.59
    …~
    -0.54
     Can
    -0.53
     can
    -0.51
    contentLoaded
    -0.51
    ganet
    -0.50
     ими
    -0.50
    ̃
    -0.49
    MockBean
    -0.49
    ecan
    -0.49
    POSITIVE LOGITS
     lenker
    0.67
     Normdatei
    0.65
    MigrationBuilder
    0.59
     colorés
    0.58
     taşlı
    0.57
     المعيارى
    0.57
     varandra
    0.56
    исленность
    0.56
     löytyy
    0.55
    новниш
    0.55
    Activations Density 0.008%

    No Known Activations