© 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. 95397
    Prev
    Next
    INDEX
    Explanations

    eye/Hindocha

    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
     limp
    -0.72
     LIM
    -0.68
    ⓧ
    -0.67
    Standard
    -0.66
     limb
    -0.65
    LIM
    -0.63
     spotted
    -0.63
     Lim
    -0.62
     Standard
    -0.62
     chor
    -0.62
    POSITIVE LOGITS
     démocr
    0.81
     varandra
    0.75
     tromper
    0.75
     médec
    0.71
     coû
    0.68
    Hentet
    0.67
     lèvres
    0.66
     enfans
    0.65
     attentes
    0.65
     dépens
    0.65
    Activations Density 1.623%

    No Known Activations