© 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. 5-CLT-HP
    7. 92754
    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
     ویکی‌پدیا
    -0.59
     transférez
    -0.54
    stdc
    -0.53
     ويكيميديا
    -0.49
     topping
    -0.49
     betweenstory
    -0.48
     Ever
    -0.47
    Remover
    -0.47
    zzleHttp
    -0.47
    ValueStyle
    -0.46
    POSITIVE LOGITS
    böz
    0.60
     affect
    0.55
     antaranya
    0.54
    Πηγή
    0.54
     kanssa
    0.54
     ermöglich
    0.53
     näky
    0.52
     légitime
    0.52
     understand
    0.51
     réussi
    0.51
    Activations Density 0.001%

    No Known Activations