© 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. 5-CLT-HP
    7. 5156
    Prev
    Next
    INDEX
    Explanations

    comma

    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
     périodes
    -0.59
    Later
    -0.59
     pilares
    -0.54
     cumplen
    -0.53
     Later
    -0.52
    later
    -0.52
     demostrado
    -0.52
    <?
    -0.52
     années
    -0.51
     later
    -0.50
    POSITIVE LOGITS
    ^(@)
    0.69
     themſelves
    0.66
     $_"
    0.63
     himſelf
    0.63
    .³
    0.62
    ISupport
    0.61
    %?
    0.60
     ſhe
    0.59
    ardless
    0.59
     ſtre
    0.59
    Activations Density 0.003%

    No Known Activations