© 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. 42856
    Prev
    Next
    INDEX
    Explanations

    ating

    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
     
    -0.68
     U
    -0.59
    el
    -0.54
    an
    -0.52
     (
    -0.52
    i
    -0.52
     of
    -0.51
    ant
    -0.50
    jo
    -0.50
    u
    -0.50
    POSITIVE LOGITS
     bezeichneter
    1.18
    Datuak
    1.16
     متعلقه
    1.16
    IVEREF
    1.12
    RectangleBorder
    1.11
    RenderAtEndOf
    1.11
     nahilalakip
    1.05
     كومونز
    1.05
    Tikang
    1.04
    WriteTagHelper
    1.03
    Activations Density 0.879%

    No Known Activations