© 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. 94222
    Prev
    Next
    INDEX
    Explanations

    pling

    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
    principalTable
    -0.84
     ſche
    -0.83
     planting
    -0.79
     Jefus
    -0.75
    ſelf
    -0.75
     Reſ
    -0.74
     doubtnut
    -0.73
    ifier
    -0.72
    ocracy
    -0.72
     iſt
    -0.72
    POSITIVE LOGITS
     N
    0.59
    autoconfigure
    0.56
     يتيمه
    0.55
    //
    0.52
     @"/
    0.51
    GEBURTSDATUM
    0.48
    oane
    0.47
     HttpNotFound
    0.46
     E
    0.45
     B
    0.44
    Activations Density 0.045%

    No Known Activations