© 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. 5-CLT-HP
    7. 92052
    Prev
    Next
    INDEX
    Explanations

    website, code

    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
     is
    -0.75
     (
    -0.72
    ↵↵
    -0.70
    '
    -0.68
     [
    -0.67
     and
    -0.66
     I
    -0.65
     has
    -0.65
     &
    -0.64
     was
    -0.63
    POSITIVE LOGITS
    TestingModule
    0.65
    Datuak
    0.58
    copg
    0.57
    jsonPath
    0.54
     meridian
    0.52
    ducers
    0.52
     WQS
    0.52
    InputBorder
    0.51
    makeConstraints
    0.50
     diplo
    0.50
    Activations Density 0.004%

    No Known Activations