© 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. 97267
    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
    TagMode
    -0.60
    +#+
    -0.54
     entanto
    -0.54
    Tē
    -0.54
    Izvori
    -0.52
    dotenv
    -0.52
     však
    -0.52
     ujednoznacz
    -0.52
     jegy
    -0.50
    Климат
    -0.49
    POSITIVE LOGITS
    EndInit
    0.64
    Portale
    0.61
    aarrggbb
    0.57
     wireType
    0.56
     estekak
    0.56
    قب
    0.54
    ocry
    0.52
    ignano
    0.52
    holds
    0.52
     Affect
    0.51
    Activations Density 0.005%

    No Known Activations