© 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. 5217
    Prev
    Next
    INDEX
    Explanations

    which

    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
     pageContext
    -0.63
     to
    -0.59
    stagland
    -0.58
     protoimpl
    -0.57
    rouwen
    -0.55
     reloadData
    -0.52
    +#+#
    -0.51
    fetchone
    -0.51
     BitmapFactory
    -0.50
    isław
    -0.50
    POSITIVE LOGITS
    الحياه
    0.65
    이션
    0.57
    UnusedPrivate
    0.53
    tvguidetime
    0.51
    Comté
    0.50
    IZON
    0.49
     countries
    0.48
     كومونز
    0.47
    uris
    0.46
    other
    0.46
    Activations Density 0.003%

    No Known Activations