© 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. 20-CLT-HP
    7. 72489
    Prev
    Next
    INDEX
    Explanations

    Copyrighted content

    np_max-act-logits · 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
     saites
    -0.68
     للمعارف
    -0.56
     мәкал
    -0.53
    astu
    -0.52
    PhysRev
    -0.51
     кӀ
    -0.49
    providedIn
    -0.49
    Geplaatst
    -0.48
     ostavi
    -0.47
     @"/
    -0.47
    POSITIVE LOGITS
    findpost
    0.64
    Datuak
    0.59
     betweenstory
    0.57
    клопе
    0.56
     Pij
    0.54
    duty
    0.52
     pleinement
    0.50
     œufs
    0.49
    afficheront
    0.49
     ErrIntOverflow
    0.49
    Activations Density 0.000%

    No Known Activations