© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 1486
    Prev
    Next
    INDEX
    Explanations

    earliest

    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
    earlier
    -1.37
     earlier
    -1.25
     earliest
    -1.16
     Earlier
    -1.13
    Earlier
    -1.02
     spurs
    -0.96
    early
    -0.92
     limb
    -0.91
     Limb
    -0.89
     spur
    -0.88
    POSITIVE LOGITS
    ness
    0.69
    SourceChecksum
    0.53
    ########.
    0.51
    ing
    0.50
    AddHtmlAttribute
    0.50
    ity
    0.48
     pinulongan
    0.48
     bou
    0.47
    fully
    0.46
    стье
    0.44
    Activations Density 0.043%

    No Known Activations