© 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. 5-CLT-HP
    7. 91412
    Prev
    Next
    INDEX
    Explanations

    technical writing excerpts

    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
     habet
    -0.71
    pisah
    -0.61
     Efq
    -0.60
     Scales
    -0.58
     whoſe
    -0.57
     mijne
    -0.57
     kasarigan
    -0.56
     Administrativna
    -0.56
     Jefus
    -0.55
     pageContext
    -0.55
    POSITIVE LOGITS
    TagMode
    0.88
     model
    0.83
     mode
    0.59
     modell
    0.57
    model
    0.57
     NSCoder
    0.57
    moveToFirst
    0.56
    endphp
    0.55
    CreateModel
    0.55
     моде
    0.55
    Activations Density 0.000%

    No Known Activations