© 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. 1-CLT-HP
    7. 9382
    Prev
    Next
    INDEX
    Explanations

    vine

    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
    OSPH
    -0.76
    +#+#
    -0.72
    fillType
    -0.66
     propOrder
    -0.65
     transfieras
    -0.64
     CURIAM
    -0.64
    lapsingToolbar
    -0.61
    TagMode
    -0.61
     disambiguazione
    -0.60
     Dop
    -0.59
    POSITIVE LOGITS
    ed
    0.56
     Waray
    0.46
    ED
    0.42
    ++
    0.42
     hand
    0.41
    })$}
    0.41
    engelsk
    0.40
    <>
    0.39
     away
    0.39
    انگلیسی
    0.39
    Activations Density 0.086%

    No Known Activations