© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 94819
    Prev
    Next
    INDEX
    Explanations

    the

    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
    ükemmel
    -0.53
    허
    -0.51
    OGND
    -0.48
     pagină
    -0.46
    ủi
    -0.45
    rsiniz
    -0.45
     automática
    -0.45
    ärna
    -0.44
    ++]=
    -0.44
     Waray
    -0.44
    POSITIVE LOGITS
    AndEndTag
    0.84
     entanto
    0.68
    AutoresizingMask
    0.66
    whereas
    0.63
     whereas
    0.57
    skjaer
    0.56
    tonode
    0.56
     оригіналу
    0.54
    aarrggbb
    0.53
    __).
    0.52
    Activations Density 0.263%

    No Known Activations