© 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. 20-CLT-HP
    7. 71875
    Prev
    Next
    INDEX
    Explanations

    Technical text

    np_max-act-logits · 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
    FormTagHelper
    -0.60
    GenerationType
    -0.56
     يتيمه
    -0.55
     gä
    -0.55
    MLLoader
    -0.54
    SpringRunner
    -0.54
    íncia
    -0.54
    writeFieldEnd
    -0.54
     baile
    -0.54
    ioterapia
    -0.53
    POSITIVE LOGITS
    nonatomic
    0.59
    RegressionTest
    0.56
     CreateTagHelper
    0.55
    AMO
    0.46
    SequentialGroup
    0.45
    News
    0.45
     news
    0.44
    Fier
    0.44
     Schar
    0.43
    цездатний
    0.43
    Activations Density 0.001%

    No Known Activations