© 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. 0-CLT-HP
    7. 43107
    Prev
    Next
    INDEX
    Explanations

    Code and non-English

    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
    tifical
    -0.62
    uncia
    -0.53
    hringer
    -0.49
    fir
    -0.48
    '][]
    -0.47
     schild
    -0.47
     HttpNotFound
    -0.47
     dirigeants
    -0.46
    рак
    -0.44
    あい
    -0.44
    POSITIVE LOGITS
    :✨
    0.93
     invokingState
    0.79
    sidemargin
    0.74
    曖昧さ回避
    0.69
    abestanden
    0.66
     Catawiki
    0.66
     SEDS
    0.65
     تضيفلها
    0.64
    InSection
    0.64
     lenker
    0.64
    Activations Density 0.813%

    No Known Activations