© 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. 91746
    Prev
    Next
    INDEX
    Explanations

    type

    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
     ویکی‌پدیا
    -0.80
     تضيفلها
    -0.74
    XmlAccessorType
    -0.73
    OOTDTY
    -0.72
    '}>
    -0.66
    )_/¯
    -0.64
    Хьажоргаш
    -0.63
    KommentareTeilen
    -0.62
     beginnetje
    -0.60
    autaire
    -0.60
    POSITIVE LOGITS
     Implemented
    0.62
     implemented
    0.59
     of
    0.58
     used
    0.57
     employed
    0.56
     performed
    0.54
    legd
    0.52
    used
    0.52
     approved
    0.52
    ir
    0.51
    Activations Density 0.004%

    No Known Activations