© 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. 15773
    Prev
    Next
    INDEX
    Explanations

    pronouns

    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
     all
    -0.56
     hasilnya
    -0.46
     antaranya
    -0.45
     All
    -0.45
    all
    -0.44
     jól
    -0.43
     semuanya
    -0.42
     ferons
    -0.42
     jäm
    -0.41
     may
    -0.41
    POSITIVE LOGITS
    #+#
    0.93
    Autoritní
    0.81
     ſche
    0.77
     nahilalakip
    0.76
     rolling
    0.76
    تقاوى
    0.74
     ſtate
    0.73
    Geplaatst
    0.73
     sandero
    0.73
     houſe
    0.73
    Activations Density 0.010%

    No Known Activations