© 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. 95257
    Prev
    Next
    INDEX
    Explanations

    om

    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
    om
    -0.88
    QPalette
    -0.68
    AutoresizingMask
    -0.67
    Архівовано
    -0.67
    CppCodeGen
    -0.63
    ImageContext
    -0.61
    })`
    -0.61
    tvguidetime
    -0.60
    ])):
    -0.58
    ArgsConstructor
    -0.57
    POSITIVE LOGITS
    s
    0.70
    sn
    0.61
    ness
    0.60
    ste
    0.56
    sha
    0.54
    sid
    0.52
    skr
    0.52
    sna
    0.52
    sk
    0.51
    sc
    0.50
    Activations Density 1.605%

    No Known Activations