© 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. 91375
    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
     at
    -0.52
     compensate
    -0.52
     keinen
    -0.51
     for
    -0.50
     make
    -0.50
     accommodate
    -0.47
     create
    -0.47
     that
    -0.47
     attract
    -0.46
     motivate
    -0.46
    POSITIVE LOGITS
    RenderAtEndOf
    0.91
    GraphicsUnit
    0.77
    \{\\
    0.76
    +#+#
    0.76
    AccessorTable
    0.75
    enderror
    0.75
    NameInMap
    0.69
    ArrowToggle
    0.68
    évaluateur
    0.68
    KeySpec
    0.67
    Activations Density 0.003%

    No Known Activations