© 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. 0-CLT-HP
    7. 42222
    Prev
    Next
    INDEX
    Explanations

    rato

    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
    rati
    -1.45
     itſelf
    -0.83
    bootstrapcdn
    -0.82
     تضيفلها
    -0.81
    Хьажоргаш
    -0.77
     purpoſe
    -0.75
    niająca
    -0.72
     ſeveral
    -0.71
     Eſ
    -0.69
     AssemblyCulture
    -0.68
    POSITIVE LOGITS
    fsp
    0.54
     te
    0.52
    торе
    0.47
     pap
    0.47
     t
    0.47
    ep
    0.47
     Te
    0.47
     er
    0.45
    thio
    0.45
     b
    0.44
    Activations Density 0.148%

    No Known Activations