© 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. 94797
    Prev
    Next
    INDEX
    Explanations

    newtheorem

    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
     Webber
    -0.45
    etak
    -0.43
    เล็ก
    -0.41
     the
    -0.40
    نظر
    -0.40
    …
    -0.39
    再
    -0.39
    zij
    -0.39
     secondary
    -0.39
     sin
    -0.38
    POSITIVE LOGITS
    findpost
    1.06
     snippetHide
    0.90
    AnchorStyles
    0.89
    SourceChecksum
    0.89
     Normdatei
    0.85
    +#+#
    0.84
    +#+
    0.81
     NSCoder
    0.81
    Geplaatst
    0.80
     BoxFit
    0.80
    Activations Density 0.159%

    No Known Activations