© 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. 42246
    Prev
    Next
    INDEX
    Explanations

    between

    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
     snippetHide
    -0.66
    ագրություններ
    -0.60
    RenderAtEndOf
    -0.59
     propOrder
    -0.58
     bicchiere
    -0.57
     jouets
    -0.54
     Réponses
    -0.53
     pemandangan
    -0.52
     rumahnya
    -0.51
     parachoque
    -0.50
    POSITIVE LOGITS
    llary
    0.67
     glycos
    0.66
     ſame
    0.65
     fruiting
    0.64
     epithe
    0.63
     ovaries
    0.63
     conformational
    0.62
     fubject
    0.62
     disulfide
    0.62
     ſub
    0.61
    Activations Density 0.225%

    No Known Activations