© 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. 97186
    Prev
    Next
    INDEX
    Explanations

    formal documents

    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
    最快更新
    -0.65
    intios
    -0.59
     ***!
    -0.58
    PostInfinity
    -0.57
    webElement
    -0.57
    zanas
    -0.56
    oa̍t
    -0.55
    medriver
    -0.54
    Gambas
    -0.54
     formally
    -0.54
    POSITIVE LOGITS
     Pain
    0.58
    Pain
    0.57
     pain
    0.55
    ChildScrollView
    0.49
     complaints
    0.46
     continúas
    0.45
    pain
    0.44
     symptoms
    0.43
     Inflammatory
    0.43
    challenges
    0.42
    Activations Density 0.000%

    No Known Activations