© 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. 3700
    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
     <=",
    -0.67
    riwal
    -0.63
    MessageOf
    -0.62
    findpost
    -0.61
     posthum
    -0.60
    recated
    -0.60
    /**
    -0.59
    chte
    -0.58
    ferenz
    -0.58
    #
    -0.58
    POSITIVE LOGITS
    ต้น
    0.46
     StringTokenizer
    0.39
    Externé
    0.38
     automatiques
    0.38
     Cortex
    0.38
     hebdomada
    0.37
     commencent
    0.36
    AccessFile
    0.36
    exact
    0.36
     générales
    0.36
    Activations Density 0.013%

    No Known Activations