© 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. 5-CLT-HP
    7. 279
    Prev
    Next
    INDEX
    Explanations

    much

    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
    ,
    -0.51
     to
    -0.47
    withIdentifier
    -0.45
    </u>
    -0.42
     as
    -0.42
     and
    -0.41
     riun
    -0.41
    (!__
    -0.40
    »).
    -0.40
    </em>
    -0.39
    POSITIVE LOGITS
     information
    0.71
     info
    0.70
    :✨
    0.69
    cookieParser
    0.69
    findpost
    0.68
    DrawerToggle
    0.66
     Comprometido
    0.63
    PreferredItem
    0.62
    ideos
    0.60
     Info
    0.59
    Activations Density 0.002%

    No Known Activations