© 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. 42738
    Prev
    Next
    INDEX
    Explanations

    public perception

    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
    RectangleBorder
    -1.16
     Recognized
    -1.02
     itſelf
    -1.01
     recognized
    -0.98
     виправивши
    -0.96
    ]='\
    -0.96
     iſt
    -0.96
     ſever
    -0.96
    ſelf
    -0.95
    ειτουργ
    -0.95
    POSITIVE LOGITS
     in
    0.70
     and
    0.62
     for
    0.59
    ally
    0.56
     I
    0.54
     on
    0.51
     progress
    0.51
     as
    0.51
     at
    0.49
     to
    0.48
    Activations Density 0.066%

    No Known Activations