© 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. 5-CLT-HP
    7. 93739
    Prev
    Next
    INDEX
    Explanations

    Line numbers

    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
    ########.
    -0.66
    цездатний
    -0.64
     محفوظة
    -0.58
    帖最后由
    -0.57
    +:+
    -0.57
     تضيفلها
    -0.57
    mybatisplus
    -0.56
     maux
    -0.54
     épaules
    -0.54
    Xna
    -0.53
    POSITIVE LOGITS
     propOrder
    0.51
    ształ
    0.51
     position
    0.48
    CHRON
    0.47
     tells
    0.47
    tagHelperRunner
    0.46
     perpetuity
    0.44
     pedig
    0.43
    salomon
    0.43
     Lázaro
    0.43
    Activations Density 0.002%

    No Known Activations