© 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. 1797
    Prev
    Next
    INDEX
    Explanations

    Code, URLs, lists

    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
    ществует
    -0.58
     EnglishChoose
    -0.53
     whofe
    -0.52
     whoſe
    -0.51
    enderror
    -0.50
     olmaz
    -0.50
    uoti
    -0.50
     giusti
    -0.49
     faſt
    -0.49
     lautet
    -0.49
    POSITIVE LOGITS
    حوالہ
    0.59
    tigungs
    0.54
     विश्वसनीयता
    0.53
    reactstrap
    0.52
     <<<<<<<<<<<<<<
    0.52
    ждую
    0.52
    󠁴
    0.52
    illigen
    0.49
    rinus
    0.49
     Италијани
    0.49
    Activations Density 0.003%

    No Known Activations