© 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. 15821
    Prev
    Next
    INDEX
    Explanations

    agreement, harmony

    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
    AutoScale
    -0.80
     समीक्षाओं
    -0.78
     تضيفلها
    -0.77
    IonicModule
    -0.73
    ValueStyle
    -0.73
     pinulongan
    -0.71
    fortawesome
    -0.71
    OGND
    -0.69
    #+#
    -0.69
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
    SerializeField
    0.56
     with
    0.46
     religiosas
    0.41
     bety
    0.40
     françaises
    0.39
     démocr
    0.39
    with
    0.39
     completas
    0.39
     journaux
    0.37
     appréci
    0.37
    Activations Density 0.011%

    No Known Activations