© 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. 92498
    Prev
    Next
    INDEX
    Explanations

    Location/movement 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
    MessageOf
    -0.47
    OpenHelper
    -0.42
     as
    -0.41
     most
    -0.40
     MBBS
    -0.40
     juvenil
    -0.38
     an
    -0.38
    pensione
    -0.38
     virtually
    -0.37
     chod
    -0.37
    POSITIVE LOGITS
     Roskov
    0.69
    WriteTagHelper
    0.68
     propOrder
    0.66
    disambiguation
    0.65
     town
    0.65
    ungszeit
    0.63
    談社
    0.63
    تقاوى
    0.62
     racines
    0.61
    ScopeManager
    0.61
    Activations Density 0.002%

    No Known Activations