© 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. 4-CLT-HP
    7. 230
    Prev
    Next
    INDEX
    Explanations

    /(

    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
    es
    -0.42
     (
    -0.42
     '
    -0.41
    liner
    -0.40
    new
    -0.39
    i
    -0.38
    t
    -0.38
    ES
    -0.38
    WR
    -0.38
     revision
    -0.38
    POSITIVE LOGITS
     kasarigan
    1.11
    rungsseite
    1.09
     Paglinawan
    0.91
     AssemblyCulture
    0.88
     betweenstory
    0.84
     photolibrary
    0.80
    }}],
    0.79
    >*/
    0.79
     ―――――
    0.79
     AssemblyTitle
    0.78
    Activations Density 0.000%

    No Known Activations