© 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. 5-CLT-HP
    7. 98077
    Prev
    Next
    INDEX
    Explanations

    Tw

    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
     Majefty
    -1.16
     purpoſe
    -1.16
     pleaſure
    -1.09
     myſelf
    -1.09
     faſt
    -1.09
     Efq
    -1.08
     Monfieur
    -1.08
     Reſ
    -1.08
     itſelf
    -1.07
     ſta
    -1.05
    POSITIVE LOGITS
    Setter
    0.42
    kmäler
    0.38
    ↵
    0.38
    結合
    0.37
    Bypass
    0.37
     jak
    0.37
     et
    0.36
     
    0.35
     una
    0.35
     mu
    0.35
    Activations Density 0.000%

    No Known Activations