© 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. 92490
    Prev
    Next
    INDEX
    Explanations

    gymnastics

    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
    دانشنامهٔ
    -1.07
    AddTagHelper
    -1.05
    Demografía
    -0.91
    原始内容存档于
    -0.86
     تضيفلها
    -0.86
    SizeF
    -0.85
    otide
    -0.85
    OGND
    -0.85
    Autoritní
    -0.85
    ftagPool
    -0.82
    POSITIVE LOGITS
    .
    0.52
     and
    0.52
     to
    0.51
     that
    0.51
     along
    0.50
     at
    0.49
     with
    0.45
     according
    0.44
    !
    0.44
     in
    0.44
    Activations Density 0.113%

    No Known Activations