© 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. 1-CLT-HP
    7. 9976
    Prev
    Next
    INDEX
    Explanations

    disorders

    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
    ztály
    -0.73
    thâu
    -0.72
    ználat
    -0.69
    Tikang
    -0.66
    erializer
    -0.65
     EconPapers
    -0.65
    "}")
    -0.64
    
    -0.64
     regeringen
    -0.61
     cremallera
    -0.61
    POSITIVE LOGITS
    KEYCODE
    0.53
     (
    0.47
    usercontent
    0.44
    TypedDataSet
    0.44
     ...
    0.44
     Vegas
    0.43
    iets
    0.43
     ("
    0.42
     —
    0.41
    MessageTagHelper
    0.41
    Activations Density 0.009%

    No Known Activations