© 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. 0-CLT-HP
    7. 94056
    Prev
    Next
    INDEX
    Explanations

    conflict and legal contexts

    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
    fs
    -0.72
    DockStyle
    -0.62
    FS
    -0.53
     fighters
    -0.50
     FS
    -0.49
     fs
    -0.49
     Donat
    -0.47
     समीक्षाएं
    -0.47
    base
    -0.44
     assure
    -0.43
    POSITIVE LOGITS
    DataAnnotations
    0.69
    ísimo
    0.65
    BASEPATH
    0.65
    Enllaços
    0.65
    Джерела
    0.64
    ']=='
    0.64
    ilisation
    0.63
     tròn
    0.63
    KURZBESCHREIBUNG
    0.63
    isque
    0.63
    Activations Density 0.073%

    No Known Activations