© 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. 76497
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
     beginnetje
    -0.72
     propOrder
    -0.70
     Савезне
    -0.65
    utilisons
    -0.64
    GEBURTSDATUM
    -0.62
    IUrlHelper
    -0.60
     Biôgrafia
    -0.59
    fillType
    -0.58
    LookAnd
    -0.58
    EDEFAULT
    -0.57
    POSITIVE LOGITS
     doing
    0.54
     content
    0.49
    titure
    0.46
     թվական
    0.45
     performing
    0.44
    מבר
    0.41
    assertIn
    0.41
     doin
    0.40
    faults
    0.40
    ombs
    0.39
    Activations Density 0.000%

    No Known Activations