© 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. 10176
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    InjectAttribute
    -0.88
     Мексичка
    -0.82
     disambiguazione
    -0.81
     Taktlose
    -0.81
    whereas
    -0.79
    parsedMessage
    -0.77
    where
    -0.77
    who
    -0.75
     AssemblyCulture
    -0.74
     виправивши
    -0.73
    POSITIVE LOGITS
     and
    0.51
     useStyles
    0.50
    WEBPACK
    0.42
    ActionBar
    0.41
     gyven
    0.40
    pidou
    0.39
    </thead>
    0.39
     chłod
    0.39
     useState
    0.38
    BorderFactory
    0.38
    Activations Density 0.009%

    No Known Activations