© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 97537
    Prev
    Next
    INDEX
    Explanations

    qualified

    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
     should
    -1.52
    should
    -1.43
     Should
    -1.40
    Should
    -1.36
     dovrebbero
    -1.25
    hould
    -1.23
     shouldBe
    -1.21
     deberían
    -1.16
     SHOULD
    -1.13
     devrait
    -1.10
    POSITIVE LOGITS
    ̀i
    0.41
    XXIII
    0.37
    лень
    0.36
     приходи
    0.35
    API
    0.35
    Sometimes
    0.34
     gran
    0.33
    त्र
    0.33
     entra
    0.33
     juri
    0.33
    Activations Density 0.133%

    No Known Activations