© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 1837
    Prev
    Next
    INDEX
    Explanations

    @

    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
     mankind
    -1.37
    @
    -1.01
     Mankind
    -0.98
     humankind
    -0.96
     @
    -0.76
    Win
    -0.65
    =@
    -0.65
     NACIONAL
    -0.63
     namely
    -0.62
    oos
    -0.61
    POSITIVE LOGITS
    ahan
    0.59
    +:+
    0.56
    SequentialGroup
    0.54
    ment
    0.52
     Audiodateien
    0.52
    ftagPool
    0.51
    MENT
    0.50
    بوابة
    0.49
    +#+
    0.48
    ôtel
    0.48
    Activations Density 0.579%

    No Known Activations