© 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. 94591
    Prev
    Next
    INDEX
    Explanations

    Reason/condition words

    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
     
    -0.68
     (
    -0.63
    ,
    -0.60
     and
    -0.56
     as
    -0.55
     -
    -0.54
     or
    -0.54
    !
    -0.54
     *
    -0.53
      
    -0.52
    POSITIVE LOGITS
     myſelf
    1.21
     raiſ
    1.13
     itſelf
    1.09
     whoſe
    1.08
     Theſe
    1.03
     ſtill
    1.02
     $_"
    1.02
     reaſon
    1.02
     faſt
    1.02
     juſt
    1.00
    Activations Density 0.056%

    No Known Activations