© 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. 5-CLT-HP
    7. 92767
    Prev
    Next
    INDEX
    Explanations

    statistics and probability

    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
    السكان
    -0.58
    ainville
    -0.54
     insurmountable
    -0.52
    avia
    -0.52
    tanleria
    -0.50
     "%"
    -0.50
    nologue
    -0.50
    oredCriteria
    -0.49
     rich
    -0.49
    viš
    -0.49
    POSITIVE LOGITS
     of
    0.65
    OGND
    0.55
    tableFuture
    0.54
     ModelExpression
    0.52
    AndEndTag
    0.51
    ագրություններ
    0.50
    gangenheit
    0.49
    ChildScrollView
    0.47
     оригіналу
    0.47
    getResource
    0.46
    Activations Density 0.002%

    No Known Activations