© 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. 15800
    Prev
    Next
    INDEX
    Explanations

    DNA and genetic sequences

    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
    FormTagHelper
    -0.83
     незавершена
    -0.82
     beginnetje
    -0.78
    帖最后由
    -0.73
    Personensuche
    -0.71
    fromnode
    -0.71
     دیکھیے
    -0.70
     consultato
    -0.70
     EconPapers
    -0.69
     AssemblyCompany
    -0.68
    POSITIVE LOGITS
     scaled
    0.51
     ranges
    0.46
     concentrated
    0.44
     clustered
    0.43
     cluster
    0.42
    huit
    0.41
    }%
    0.41
     lifeline
    0.41
    ))->
    0.40
    ẵn
    0.40
    Activations Density 0.079%

    No Known Activations