© 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. 98291
    Prev
    Next
    INDEX
    Explanations

    website appearance

    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
     يتيمه
    -0.62
    <bos>
    -0.60
    Geplaatst
    -0.59
     Wikimedijinoj
    -0.59
    AsUp
    -0.59
    ModelSerializer
    -0.58
    abestanden
    -0.57
    WebVitals
    -0.56
     estekak
    -0.55
     bezeichneter
    -0.54
    POSITIVE LOGITS
    PYX
    0.72
     Paix
    0.49
    netbeans
    0.48
    gator
    0.48
     Gegenteil
    0.48
    insegna
    0.48
     combining
    0.47
     aVar
    0.46
    schild
    0.46
    ẻo
    0.45
    Activations Density 0.002%

    No Known Activations