© 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. 0-CLT-HP
    7. 41715
    Prev
    Next
    INDEX
    Explanations

    measurements

    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
     variables
    -1.31
     Variables
    -1.19
    variables
    -1.13
     Parameters
    -1.04
     parameters
    -1.02
    Parameters
    -0.93
    Variables
    -0.93
    factors
    -0.92
     VARIABLES
    -0.92
     factors
    -0.85
    POSITIVE LOGITS
     to
    0.58
     for
    0.49
     it
    0.46
    ,
    0.46
     '
    0.45
     giving
    0.45
     in
    0.44
     at
    0.44
     that
    0.43
    -
    0.43
    Activations Density 0.099%

    No Known Activations