© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1967
    Prev
    Next
    INDEX
    Explanations

    seques

    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
    ########.
    -0.70
    izen
    -0.66
    providedIn
    -0.65
    ::_('
    -0.62
     endwhile
    -0.56
    Архівовано
    -0.56
    basicConfig
    -0.55
    uden
    -0.54
     seques
    -0.54
    YON
    -0.54
    POSITIVE LOGITS
    trum
    0.52
    horesis
    0.50
    findpost
    0.49
    throwing
    0.49
    ftagPool
    0.47
    ctomy
    0.46
    cet
    0.45
     kanyang
    0.44
    trou
    0.44
    cillors
    0.43
    Activations Density 0.067%

    No Known Activations