© 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. 20-CLT-HP
    7. 74852
    Prev
    Next
    INDEX
    Explanations

    non-English

    np_max-act-logits · 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
    ########.
    -0.75
    #+#
    -0.63
     विश्वसनीयता
    -0.62
    RenderAtEndOf
    -0.62
    :+:
    -0.62
    skjaer
    -0.60
    <_>
    -0.59
     esternos
    -0.59
     EconPapers
    -0.57
     فريبيس
    -0.56
    POSITIVE LOGITS
    SuppressMessage
    0.56
    prnewswire
    0.52
    umumkan
    0.45
     trasladado
    0.45
     qualify
    0.44
     Wicidata
    0.43
    각주
    0.42
     oublier
    0.42
     tür
    0.41
    mHandler
    0.41
    Activations Density 0.000%

    No Known Activations