© 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. 5773
    Prev
    Next
    INDEX
    Explanations

    early/first

    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
    -0.59
     has
    -0.53
     were
    -0.51
     was
    -0.51
     cellpadding
    -0.50
     MainAxisSize
    -0.49
    antaranya
    -0.49
     one
    -0.49
    one
    -0.48
     resourceCulture
    -0.47
    POSITIVE LOGITS
     autorytatywna
    0.67
     ModelExpression
    0.60
     blow
    0.60
    FieldDescriptor
    0.58
     sparks
    0.57
    OGND
    0.56
     step
    0.53
    carded
    0.52
    invokeLater
    0.52
    WindowEvent
    0.52
    Activations Density 0.001%

    No Known Activations