© 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. 0-CLT-HP
    7. 43485
    Prev
    Next
    INDEX
    Explanations

    from

    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
     from
    -1.64
    from
    -1.42
    From
    -1.10
     från
    -1.10
     FROM
    -1.04
    จาก
    -0.97
    从
    -0.92
     From
    -0.90
     dari
    -0.84
     از
    -0.84
    POSITIVE LOGITS
     the
    1.00
     our
    0.76
     an
    0.73
     a
    0.71
     afar
    0.68
     my
    0.66
     your
    0.63
     his
    0.63
     us
    0.61
     what
    0.61
    Activations Density 0.334%

    No Known Activations