© 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. 91854
    Prev
    Next
    INDEX
    Explanations

    and

    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
    -0.96
     are
    -0.80
     it
    -0.79
     was
    -0.70
     has
    -0.68
    are
    -0.67
     were
    -0.60
     the
    -0.60
     could
    -0.59
     there
    -0.58
    POSITIVE LOGITS
     with
    0.79
     الرياضيه
    0.75
     averaging
    0.69
     weighing
    0.69
     costing
    0.67
     focusing
    0.66
     forgetting
    0.65
    StoryboardSegue
    0.65
     devoting
    0.65
     raiſ
    0.64
    Activations Density 0.001%

    No Known Activations