© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 2936
    Prev
    Next
    INDEX
    Explanations

    location 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
     naught
    -0.39
    MenuInflater
    -0.38
     destination
    -0.37
     mood
    -0.36
    Anything
    -0.36
     car
    -0.36
     area
    -0.35
    OUR
    -0.34
     rim
    -0.34
     spec
    -0.33
    POSITIVE LOGITS
    AndEndTag
    0.92
     its
    0.78
    ConstraintMaker
    0.77
    +#+#
    0.75
    IntoConstraints
    0.74
     estekak
    0.74
    AddHtmlAttribute
    0.73
    featureID
    0.73
    KommentareTeilen
    0.71
     صوتيه
    0.71
    Activations Density 0.002%

    No Known Activations