© 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. 92376
    Prev
    Next
    INDEX
    Explanations

    commas

    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
     or
    -0.52
     is
    -0.50
     
    -0.49
     en
    -0.48
     un
    -0.43
     for
    -0.42
     by
    -0.41
     ver
    -0.41
    ')
    -0.41
    ()));
    -0.41
    POSITIVE LOGITS
     Italijanski
    1.07
    帖最后由
    1.03
     houſe
    1.02
     myſelf
    1.02
     pleaſure
    0.98
     snippetHide
    0.97
    AndEndTag
    0.96
    Vidite
    0.94
    styleType
    0.88
     reaſon
    0.88
    Activations Density 0.002%

    No Known Activations