© 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. 9654
    Prev
    Next
    INDEX
    Explanations

    Sh

    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
    ab
    -0.54
    æl
    -0.52
     sh
    -0.49
    ibar
    -0.47
     Sh
    -0.47
     de
    -0.47
    strptime
    -0.46
    bit
    -0.45
     Sha
    -0.45
    avir
    -0.45
    POSITIVE LOGITS
    +#+#
    0.94
     Walkover
    0.83
     transférez
    0.70
     Numerade
    0.70
    SharedCtor
    0.69
    orsese
    0.69
    RegressionTest
    0.68
    uxxxx
    0.68
    OGND
    0.66
     ModelRenderer
    0.66
    Activations Density 0.013%

    No Known Activations