© 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. 4-CLT-HP
    7. 305
    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
    apunov
    -0.76
    Personendaten
    -0.74
     oprot
    -0.74
     дописавши
    -0.71
    BeginContext
    -0.71
    styleType
    -0.70
     становника
    -0.68
     resourceCulture
    -0.68
    DoubleQuotes
    -0.68
    PerformLayout
    -0.65
    POSITIVE LOGITS
     the
    0.82
     an
    0.67
     yet
    0.66
     a
    0.64
     not
    0.57
     is
    0.54
     Yet
    0.52
    Yet
    0.51
     that
    0.50
    yet
    0.50
    Activations Density 0.002%

    No Known Activations