© 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. 1-CLT-HP
    7. 9430
    Prev
    Next
    INDEX
    Explanations

    éra

    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
     SMART
    -1.06
    SMART
    -0.84
     parseFrom
    -0.53
    gota
    -0.45
     atoi
    -0.45
    df
    -0.45
     Grafen
    -0.44
    %?
    -0.43
    pablo
    -0.42
    ToAction
    -0.42
    POSITIVE LOGITS
    ies
    0.79
    iest
    0.76
    ie
    0.74
    i
    0.70
    ians
    0.69
    ier
    0.69
    Diweddarwch
    0.68
    ize
    0.67
    protoimpl
    0.66
    ials
    0.66
    Activations Density 0.074%

    No Known Activations