© 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. 20-CLT-HP
    7. 77670
    Prev
    Next
    INDEX
    Explanations

    Code and technical descriptions

    np_max-act-logits · 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
     Normdatei
    -0.76
    ReusableCell
    -0.68
     autorytatywna
    -0.68
    nodoc
    -0.66
    Newswire
    -0.65
    tonsoft
    -0.65
    ếng
    -0.60
    onViewCreated
    -0.60
    ToAction
    -0.60
    actionMode
    -0.59
    POSITIVE LOGITS
    ghe
    0.55
    BagConstraints
    0.54
    Tikang
    0.41
    pen
    0.41
    pies
    0.41
    пе
    0.40
    BindingResult
    0.40
     PyLong
    0.39
    يميديا
    0.39
     sebel
    0.39
    Activations Density 0.000%

    No Known Activations