© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92985
    Prev
    Next
    INDEX
    Explanations

    something

    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
     something
    -2.44
    something
    -2.30
     Something
    -2.06
    Something
    -2.05
     qualcosa
    -1.87
     SOMETHING
    -1.77
     anything
    -1.67
     things
    -1.63
     somethin
    -1.60
     everything
    -1.47
    POSITIVE LOGITS
     else
    0.95
     in
    0.80
     that
    0.75
     to
    0.72
     about
    0.71
     from
    0.65
     on
    0.61
     like
    0.60
     for
    0.59
     at
    0.58
    Activations Density 0.061%

    No Known Activations