© 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. 42670
    Prev
    Next
    INDEX
    Explanations

    such

    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
     for
    -0.65
     and
    -0.62
     poitrine
    -0.61
    typeparam
    -0.57
    ed
    -0.55
    principalTable
    -0.55
    e
    -0.54
    ~
    -0.54
    opsida
    -0.54
     is
    -0.53
    POSITIVE LOGITS
     faſt
    0.90
     purpoſe
    0.85
     myſelf
    0.85
     ſche
    0.80
     fevere
    0.79
     ſever
    0.78
     poffible
    0.75
     neceffary
    0.75
     fubject
    0.75
     raiſ
    0.74
    Activations Density 0.269%

    No Known Activations