© 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. 93698
    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
     intégr
    -0.50
    Xna
    -0.50
     ModelRenderer
    -0.48
    intios
    -0.47
     spéciaux
    -0.47
     fallu
    -0.45
    mybatisplus
    -0.45
    ISupport
    -0.45
     flesta
    -0.45
    bute
    -0.45
    POSITIVE LOGITS
    Jeografia
    0.58
    indd
    0.57
    GEBURTSDATUM
    0.56
     considering
    0.56
    MENAFN
    0.55
     assigning
    0.54
    considering
    0.54
    principalColumn
    0.54
     plotting
    0.53
     autobiography
    0.51
    Activations Density 0.000%

    No Known Activations