© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 12382
    Prev
    Next
    INDEX
    Explanations

    naming

    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
    addPreferredGap
    -0.53
     VEGET
    -0.53
     useCallback
    -0.51
     tetanus
    -0.49
    #__
    -0.49
    +#+#
    -0.48
    URLException
    -0.48
    ymal
    -0.47
    beforeEach
    -0.47
    __).
    -0.47
    POSITIVE LOGITS
     disambiguazione
    0.71
    check
    0.63
    checks
    0.62
    hand
    0.62
    post
    0.61
    lines
    0.59
    plate
    0.58
    pool
    0.57
    words
    0.57
    word
    0.57
    Activations Density 0.009%

    No Known Activations