© 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. 95336
    Prev
    Next
    INDEX
    Explanations

    clef

    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
     clef
    -0.86
    VersionUID
    -0.70
    PTSD
    -0.64
    MLLoader
    -0.63
    mybatisplus
    -0.61
    setContentView
    -0.60
    makeText
    -0.56
    CppMethod
    -0.54
     år
    -0.54
    zbęd
    -0.52
    POSITIVE LOGITS
    RTDA
    0.52
    [](
    0.50
    smith
    0.50
     behandling
    0.50
     DPM
    0.50
     glass
    0.49
    Ufficio
    0.49
    sense
    0.49
    ?[
    0.48
     [](
    0.48
    Activations Density 0.273%

    No Known Activations