© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4639
    Prev
    Next
    INDEX
    Explanations

    historical figures

    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
     betweenstory
    -0.65
     Armageddon
    -0.62
     Parenthood
    -0.61
    ьаж
    -0.58
     мәкал
    -0.57
    #+#
    -0.56
    sság
    -0.55
     Methanol
    -0.55
     tremp
    -0.55
     Ceremonies
    -0.55
    POSITIVE LOGITS
    tagHelperRunner
    0.63
     viewHolder
    0.58
    __':
    0.50
    ++);
    0.49
     eigentlich
    0.49
    rawDesc
    0.49
    _));
    0.48
    />
    0.46
    '])->
    0.46
    ",&
    0.46
    Activations Density 0.002%

    No Known Activations