© 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
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 42865
    Prev
    Next
    INDEX
    Explanations

    large quantities

    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
     numerous
    -1.28
     innumerable
    -1.27
     countless
    -1.24
    Numerous
    -1.18
     many
    -1.13
    many
    -1.08
     myriad
    -1.06
     Numerous
    -1.05
     multitude
    -0.97
    numer
    -0.97
    POSITIVE LOGITS
    <bos>
    0.50
    tod
    0.47
    ames
    0.45
    мят
    0.44
     lymphoid
    0.44
    requireNonNull
    0.43
    InputStream
    0.43
     detainees
    0.43
     Nearby
    0.43
     circumstances
    0.43
    Activations Density 0.997%

    No Known Activations