© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 14351
    Prev
    Next
    INDEX
    Explanations

    burden

    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
     burden
    -0.69
    pement
    -0.69
    +#+#
    -0.69
    цездатний
    -0.67
    SequentialGroup
    -0.65
    verwijspagina
    -0.64
     trident
    -0.63
     armature
    -0.63
     Guel
    -0.60
    })->
    -0.60
    POSITIVE LOGITS
     of
    0.87
    ing
    0.78
     on
    0.72
    AddTagHelper
    0.61
     to
    0.59
     placed
    0.56
     FetchType
    0.56
     for
    0.49
    ting
    0.48
    ########.
    0.47
    Activations Density 0.001%

    No Known Activations