© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4151
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
     umě
    -0.50
    zionamento
    -0.47
    withOpacity
    -0.47
     placée
    -0.46
    Бахар
    -0.46
    abestanden
    -0.46
    гава
    -0.46
     stranger
    -0.46
    bewerken
    -0.44
    peer
    -0.43
    POSITIVE LOGITS
     save
    0.93
     saves
    0.73
     saving
    0.65
     preserve
    0.65
    save
    0.65
     stabilize
    0.65
     conserve
    0.64
     Save
    0.60
    SAVE
    0.60
     SAVE
    0.59
    Activations Density 0.003%

    No Known Activations