© 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. 43421
    Prev
    Next
    INDEX
    Explanations

    dimension

    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
     dimension
    -1.74
    dimension
    -1.59
     Dimension
    -1.50
     dimensions
    -1.45
    Dimension
    -1.41
     Dimensions
    -1.35
     dimensión
    -1.34
     DIMENSION
    -1.32
     dimensional
    -1.27
    dimensional
    -1.23
    POSITIVE LOGITS
    ########.
    0.51
     semej
    0.49
     BoxFit
    0.49
    ReusableCell
    0.49
    heber
    0.47
    paramref
    0.45
     потер
    0.42
    stdio
    0.42
     in
    0.42
    aternion
    0.42
    Activations Density 0.470%

    No Known Activations