© 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. 42651
    Prev
    Next
    INDEX
    Explanations

    genetics and biology

    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
    genes
    -0.89
    hems
    -0.59
     words
    -0.59
     voices
    -0.58
    hagen
    -0.57
    gene
    -0.56
    hea
    -0.54
    cas
    -0.53
    uaa
    -0.53
     phrases
    -0.53
    POSITIVE LOGITS
     löytyy
    0.65
     henkil
    0.62
     väli
    0.59
     оригіналу
    0.59
     récompenses
    0.57
    urally
    0.56
     positivas
    0.55
     decorativas
    0.54
     motivadoras
    0.54
     pourrais
    0.54
    Activations Density 0.177%

    No Known Activations