© 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. 5093
    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
     Normdatei
    -0.75
    écnicas
    -0.52
    PDATE
    -0.52
     Anexo
    -0.50
    wiſe
    -0.48
     Pingback
    -0.48
    WindowConstants
    -0.46
    WSGI
    -0.45
     فهرست
    -0.45
    AndView
    -0.44
    POSITIVE LOGITS
     Their
    1.09
     Its
    0.94
     His
    0.94
     Your
    0.84
    His
    0.76
     Her
    0.76
    Their
    0.76
     Himself
    0.73
     Myself
    0.72
     Itself
    0.72
    Activations Density 0.005%

    No Known Activations