© 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. 101
    Prev
    Next
    INDEX
    Explanations

    usr

    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
    ########.
    -0.67
     insuffisamment
    -0.62
    IVEREF
    -0.56
    formik
    -0.55
    MathML
    -0.52
    joven
    -0.50
     distanciation
    -0.50
     rospy
    -0.50
    //
    -0.49
    Šaltiniai
    -0.49
    POSITIVE LOGITS
     to
    0.64
     be
    0.59
     boomers
    0.58
     bees
    0.54
    weds
    0.53
    bees
    0.51
    Бахар
    0.51
    bolistas
    0.50
    bies
    0.49
     brides
    0.49
    Activations Density 0.002%

    No Known Activations