© 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. 5186
    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
     Meksiku
    -0.54
    Later
    -0.48
     समीक्षक
    -0.47
    AndroidJUnit
    -0.47
     later
    -0.45
    ⓧ
    -0.44
     kés
    -0.43
    Geplaatst
    -0.41
    awaiter
    -0.41
    FailureListener
    -0.41
    POSITIVE LOGITS
    RectangleBorder
    0.77
    ?";
    0.67
     BoxDecoration
    0.66
    Erreferentziak
    0.65
    ientôt
    0.64
    */;
    0.63
     $_"
    0.63
     متعلقه
    0.61
     Kecil
    0.60
    Année
    0.60
    Activations Density 0.010%

    No Known Activations