© 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. 1-CLT-HP
    7. 9249
    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
     tartalomajánló
    -0.85
    Tikang
    -0.84
     rajut
    -0.72
    jalá
    -0.69
    guió
    -0.69
     disambiguazione
    -0.69
     igång
    -0.68
    #
    -0.67
    oneofs
    -0.66
    quelles
    -0.66
    POSITIVE LOGITS
     warts
    0.46
     the
    0.46
    NullException
    0.43
    ियो
    0.42
    tes
    0.42
     nod
    0.40
     diabetes
    0.40
     pizza
    0.39
    EndContext
    0.39
     tan
    0.38
    Activations Density 0.090%

    No Known Activations