© 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. 92886
    Prev
    Next
    INDEX
    Explanations

    trending

    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
     trending
    -1.52
    Trending
    -1.40
    trending
    -1.28
     Trending
    -1.18
    httphttps
    -0.67
     nakalista
    -0.64
    parsedMessage
    -0.63
    SBATCH
    -0.63
    +#+#
    -0.61
     pleaf
    -0.61
    POSITIVE LOGITS
     tqdm
    0.50
    altezza
    0.48
     opa
    0.47
    opa
    0.47
    zko
    0.46
    Farewell
    0.46
     Congratulations
    0.44
    )->
    0.44
    HtmlAttribute
    0.43
    towe
    0.43
    Activations Density 0.104%

    No Known Activations