© 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. 4-CLT-HP
    7. 17
    Prev
    Next
    INDEX
    Explanations

    ide

    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
     fratelli
    -0.62
    ValueGeneration
    -0.60
    sschule
    -0.60
     mauvaises
    -0.59
     vetorial
    -0.59
     pleaſure
    -0.58
     Paglinawan
    -0.58
     igång
    -0.58
     genoux
    -0.57
     purpoſe
    -0.56
    POSITIVE LOGITS
    CGRectMake
    0.58
    uxxxx
    0.57
     comb
    0.57
    Билгалдахарш
    0.53
    قایناقلار
    0.52
    BeginContext
    0.51
    rosh
    0.50
    BuildContext
    0.50
    Див
    0.49
     CGRectMake
    0.49
    Activations Density 0.001%

    No Known Activations