© 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. 92723
    Prev
    Next
    INDEX
    Explanations

    data transformation

    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
    viewDidLoad
    -0.44
    abestanden
    -0.43
    ífer
    -0.42
     jarang
    -0.41
    onsored
    -0.40
    SPONSORED
    -0.40
    ciss
    -0.40
    digans
    -0.39
    SPATH
    -0.39
    所在
    -0.38
    POSITIVE LOGITS
     المعيارى
    0.80
    TargetException
    0.69
    HandlerContext
    0.68
    astronomie
    0.66
    extAlignment
    0.64
     electronically
    0.63
     optically
    0.62
     TextAppearance
    0.61
     digitally
    0.60
    itinéraire
    0.60
    Activations Density 0.003%

    No Known Activations