© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 4968
    Prev
    Next
    INDEX
    Explanations

    adne

    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
     nakalista
    -0.62
    UVWXYZ
    -0.57
    FailureListener
    -0.56
    saraba
    -0.53
     fixer
    -0.51
    siella
    -0.51
     planas
    -0.48
    ViewFeatures
    -0.46
    brigens
    -0.45
     понятия
    -0.45
    POSITIVE LOGITS
    ]--;
    0.66
    +#+
    0.65
    #+#
    0.64
     referenties
    0.64
    migrationBuilder
    0.59
     Waray
    0.56
    сшта
    0.55
     numberOfRows
    0.53
    vestream
    0.53
     baum
    0.52
    Activations Density 0.001%

    No Known Activations