© 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. 97298
    Prev
    Next
    INDEX
    Explanations

    (

    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
    ]")]
    -0.65
    AndEndTag
    -0.64
    idosis
    -0.54
     considérons
    -0.50
    modb
    -0.49
    UnsafeEnabled
    -0.48
     padd
    -0.48
     FishBase
    -0.47
     <=",
    -0.47
    LabelTagHelper
    -0.47
    POSITIVE LOGITS
    Примітки
    0.57
     illet
    0.52
     [''],
    0.52
    CMC
    0.50
    احبه
    0.50
    клопе
    0.50
     HttpNotFound
    0.48
    SPECTION
    0.48
    GraphQL
    0.48
     Micho
    0.47
    Activations Density 0.008%

    No Known Activations