© 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. 76709
    Prev
    Next
    INDEX
    Explanations

    foreign language/code snippets

    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
    tvguidetime
    -0.82
     tartalomajánló
    -0.80
    WriteBarrier
    -0.75
     visibilité
    -0.75
     décédé
    -0.74
     fhew
    -0.73
     feveral
    -0.72
     themſelves
    -0.72
     newOwner
    -0.72
     ftate
    -0.71
    POSITIVE LOGITS
     оригіналу
    0.43
     plante
    0.37
    cians
    0.34
    LOYEES
    0.33
    stals
    0.33
    ValueStyle
    0.33
    Pyx
    0.32
    standers
    0.32
    ...</
    0.30
    gypti
    0.30
    Activations Density 0.000%

    No Known Activations