© 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. 4-CLT-HP
    7. 875
    Prev
    Next
    INDEX
    Explanations

    Caution/Obligation/Permission

    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
    WebElementEntity
    -0.77
     utafitiHapana
    -0.63
     Remind
    -0.60
    ="#"><
    -0.59
     Practically
    -0.59
    InstrumentedTest
    -0.58
     "");
    -0.58
    Revenir
    -0.57
    ("${
    -0.56
     consultato
    -0.55
    POSITIVE LOGITS
     use
    0.50
     yet
    0.50
    seende
    0.49
    IntoConstraints
    0.48
    UTERS
    0.45
    用
    0.45
     sust
    0.45
     GoogleFonts
    0.45
    StreetMap
    0.44
    реб
    0.42
    Activations Density 0.037%

    No Known Activations