© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 75536
    Prev
    Next
    INDEX
    Explanations

    South

    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
    Vidite
    -0.70
    enumi
    -0.67
     nahilalakip
    -0.66
    Portale
    -0.66
     незавершена
    -0.64
     Roskov
    -0.64
     Administrativna
    -0.63
     Мексичка
    -0.63
    ISupport
    -0.62
    VIAF
    -0.59
    POSITIVE LOGITS
     getM
    0.48
    TacToe
    0.47
    pota
    0.47
     grounding
    0.42
    gel
    0.39
    AVA
    0.39
    zez
    0.39
    goto
    0.39
     طو
    0.38
    erden
    0.38
    Activations Density 0.003%

    No Known Activations