© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 92398
    Prev
    Next
    INDEX
    Explanations

    "Dep" and height related

    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
     BoxFit
    -0.66
     height
    -0.66
     clothes
    -0.61
    awtextra
    -0.57
     Höhe
    -0.54
    styleType
    -0.52
     Monfieur
    -0.49
    PUT
    -0.48
     leaft
    -0.47
    ogos
    -0.47
    POSITIVE LOGITS
    :+:
    0.63
     <<<<<<<<<<<<<<
    0.57
     mapStateToProps
    0.55
    quakes
    0.54
    postsleuth
    0.54
    setopt
    0.53
     ویکی‌پدی
    0.53
    VideoCapture
    0.51
    celotti
    0.50
    FromArgb
    0.50
    Activations Density 0.258%

    No Known Activations