© 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. 93261
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    出版年
    -0.69
     Came
    -0.58
    KommentareTeilen
    -0.56
     utafitiHapana
    -0.53
    olverine
    -0.52
    ommen
    -0.52
    mbic
    -0.52
    躇
    -0.52
    onCreate
    -0.51
    Came
    -0.51
    POSITIVE LOGITS
    matically
    0.59
    ologically
    0.56
     چنین
    0.51
     متعلقه
    0.51
    ftagPool
    0.50
    Geplaatst
    0.48
    sizeCache
    0.47
    省市镇
    0.45
    Havolalar
    0.44
     rağmen
    0.44
    Activations Density 0.007%

    No Known Activations