© 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. 20-CLT-HP
    7. 76300
    Prev
    Next
    INDEX
    Explanations

    a

    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
     للمعارف
    -0.69
     vPvB
    -0.69
     estekak
    -0.67
     препратки
    -0.67
    colgroup
    -0.66
     Gaps
    -0.65
    зулта
    -0.64
     disadvantages
    -0.64
    Geplaatst
    -0.63
     فريبيس
    -0.60
    POSITIVE LOGITS
     leg
    0.70
     survival
    0.58
     decided
    0.55
     deciso
    0.51
     Unies
    0.49
    decided
    0.48
     selective
    0.45
     step
    0.44
    Pyx
    0.42
     decides
    0.42
    Activations Density 0.000%

    No Known Activations