© 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. 4602
    Prev
    Next
    INDEX
    Explanations

    comparison, differentiation

    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
     виправивши
    -0.78
     betweenstory
    -0.69
     متعلقه
    -0.69
    сылкі
    -0.59
     שוליים
    -0.58
     mại
    -0.57
    IntoConstraints
    -0.57
    reszcie
    -0.55
    tagHelperRunner
    -0.54
     noqa
    -0.53
    POSITIVE LOGITS
     year
    0.75
     month
    0.58
     years
    0.58
    onedDateTime
    0.54
    year
    0.54
     år
    0.53
     semester
    0.52
    kuuta
    0.52
     annum
    0.51
     week
    0.51
    Activations Density 0.004%

    No Known Activations