© 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. 984
    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
     intptr
    -0.52
     propOrder
    -0.52
    záll
    -0.48
     Âge
    -0.47
    utilisons
    -0.47
     unknownFields
    -0.46
    tempts
    -0.45
     siguientes
    -0.45
    درسة
    -0.44
    Brainz
    -0.44
    POSITIVE LOGITS
    <bos>
    0.69
     this
    0.63
     that
    0.60
     helping
    0.56
     enhancing
    0.53
     Helping
    0.52
    klis
    0.52
     aiding
    0.52
     тази
    0.51
    こちらも
    0.51
    Activations Density 0.002%

    No Known Activations