© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 1360
    Prev
    Next
    INDEX
    Explanations

    strangeness

    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
    дження
    -0.40
    publicain
    -0.38
     peores
    -0.36
    utivo
    -0.35
     ready
    -0.34
     chirurgie
    -0.33
     brake
    -0.33
    tex
    -0.33
     ślub
    -0.32
     thủy
    -0.32
    POSITIVE LOGITS
     wireType
    0.89
     étrange
    0.81
     Weird
    0.80
     Strange
    0.80
    Weird
    0.80
    readystatechange
    0.77
    Strange
    0.77
     itſelf
    0.77
     strangely
    0.76
    ViewInit
    0.76
    Activations Density 0.015%

    No Known Activations