© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1171
    Prev
    Next
    INDEX
    Explanations

    Opinions/justifications/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
    enumi
    -0.66
    rungsseite
    -0.53
    Finally
    -0.49
     Finally
    -0.49
     aihe
    -0.49
     tarko
    -0.48
    </caption>
    -0.48
    的是
    -0.47
     kuitenkin
    -0.47
    ífero
    -0.47
    POSITIVE LOGITS
    ,
    0.78
     how
    0.74
     why
    0.73
     who
    0.69
    ########.
    0.65
     it
    0.63
    antMatchers
    0.63
     wtf
    0.61
    onViewCreated
    0.60
     syphilis
    0.60
    Activations Density 0.016%

    No Known Activations