© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 6250
    Prev
    Next
    INDEX
    Explanations

    describe

    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
    Negative Logits
    ########.
    -0.68
     unknownFields
    -0.65
    +#+#
    -0.60
    itability
    -0.60
    yntaxException
    -0.59
     AssemblyCulture
    -0.58
     AssemblyVersion
    -0.57
    InitStruct
    -0.57
     Conservancy
    -0.56
     piaci
    -0.56
    POSITIVE LOGITS
    ody
    0.57
    odes
    0.53
    image
    0.53
    ode
    0.52
    od
    0.50
     يتيمه
    0.50
    vode
    0.49
    rod
    0.46
     egret
    0.46
    images
    0.45
    Activations Density 0.001%

    No Known Activations