© 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. 5-CLT-HP
    7. 2879
    Prev
    Next
    INDEX
    Explanations

    code or keys

    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
     виправивши
    -1.06
    +#+#
    -1.05
     للمعارف
    -0.97
     متعلقه
    -0.93
    featureID
    -0.90
     ویکی‌پدیای
    -0.89
    tagHelperRunner
    -0.87
    parsedMessage
    -0.81
    Autoritní
    -0.80
    expandindo
    -0.80
    POSITIVE LOGITS
    CU
    0.43
    pV
    0.42
    pv
    0.41
    J
    0.41
    xp
    0.40
    Qi
    0.40
    EL
    0.39
    EV
    0.39
    cu
    0.39
    9
    0.38
    Activations Density 0.045%

    No Known Activations