© 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. 42384
    Prev
    Next
    INDEX
    Explanations

    acceleration

    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
    antMatchers
    -0.79
    writeField
    -0.66
    Vidite
    -0.65
     accelerated
    -0.64
    出版年
    -0.64
    ftagPool
    -0.63
    thansa
    -0.59
     accelerating
    -0.58
    #+#
    -0.58
     críticos
    -0.57
    POSITIVE LOGITS
     myſelf
    1.15
     itſelf
    1.01
     leaſt
    0.98
     Jefus
    0.96
     Diſ
    0.92
     Anſ
    0.92
     Majefty
    0.92
     himſelf
    0.91
     Efq
    0.91
     Reſ
    0.91
    Activations Density 0.034%

    No Known Activations