© 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. 4646
    Prev
    Next
    INDEX
    Explanations

    seeing/understanding

    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
     how
    -0.53
    argli
    -0.49
     the
    -0.46
     ways
    -0.46
     façons
    -0.45
     كورة
    -0.45
     an
    -0.44
    ony
    -0.44
     sidste
    -0.44
     étoient
    -0.43
    POSITIVE LOGITS
    ChildScrollView
    0.86
    SequentialGroup
    0.84
    fjspx
    0.78
    Bronnen
    0.67
    MLLoader
    0.65
     MainAxisSize
    0.63
     ExecuteAsync
    0.61
    IsContent
    0.61
    initializeApp
    0.59
     <<<<<<<<<<<<<<
    0.58
    Activations Density 0.001%

    No Known Activations