© 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. 4-CLT-HP
    7. 4893
    Prev
    Next
    INDEX
    Explanations

    trouble

    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
     Collapse
    -0.51
    nehm
    -0.50
    nachweis
    -0.46
    +#+#
    -0.46
    suchen
    -0.46
    arsus
    -0.45
     su
    -0.44
    rean
    -0.44
     and
    -0.42
    orphism
    -0.42
    POSITIVE LOGITS
     começou
    0.66
     começaram
    0.63
     empezó
    0.62
     comenzó
    0.58
     started
    0.58
    makers
    0.58
    started
    0.57
    maker
    0.57
    脚注の使い方
    0.57
    ValueGenerated
    0.57
    Activations Density 0.002%

    No Known Activations