© 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. 92782
    Prev
    Next
    INDEX
    Explanations

    No

    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
     PLWABN
    -0.66
    يميديا
    -0.64
     catég
    -0.64
     pinulongan
    -0.62
    SizeMode
    -0.62
    SourceChecksum
    -0.62
    saraba
    -0.61
    ometal
    -0.61
     hObject
    -0.60
     fieldName
    -0.60
    POSITIVE LOGITS
     
    0.50
    withstanding
    0.46
    .!
    0.45
    SerializedName
    0.43
     fours
    0.42
     nine
    0.42
     ten
    0.42
    sund
    0.42
    theless
    0.39
     four
    0.38
    Activations Density 0.008%

    No Known Activations