© 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. 1-CLT-HP
    7. 15720
    Prev
    Next
    INDEX
    Explanations

    Allen

    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
     Allen
    -1.00
    Allen
    -0.97
     ALLEN
    -0.77
    copg
    -0.77
    ALLEN
    -0.74
    allen
    -0.73
     allen
    -0.69
    AFX
    -0.63
    apimachinery
    -0.63
     ISNI
    -0.62
    POSITIVE LOGITS
     morire
    0.52
    ners
    0.46
     duvar
    0.46
     câte
    0.45
     כן
    0.45
     cementerio
    0.45
     unele
    0.44
     tradicionais
    0.44
     traditionnels
    0.44
    Portale
    0.44
    Activations Density 0.033%

    No Known Activations