© 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. 20-CLT-HP
    7. 72061
    Prev
    Next
    INDEX
    Explanations

    technical contexts

    np_max-act-logits · 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
     esterni
    -0.50
    ModelAttribute
    -0.50
     kū
    -0.48
    Архівовано
    -0.47
    펙
    -0.47
    цезда
    -0.46
     and
    -0.46
     Outs
    -0.45
     soggior
    -0.45
    flüs
    -0.43
    POSITIVE LOGITS
     tartalomajánló
    0.53
    jerg
    0.52
    itez
    0.51
     rangs
    0.51
    RTLD
    0.51
     Ti
    0.50
    timme
    0.49
     Vö
    0.47
     ligiloj
    0.46
    rawl
    0.46
    Activations Density 0.001%

    No Known Activations