© 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. 42482
    Prev
    Next
    INDEX
    Explanations

    A

    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
     firma
    -1.31
    firma
    -0.79
     Firma
    -0.71
    Firma
    -0.71
     Ch
    -0.53
     West
    -0.53
     de
    -0.51
     Chicago
    -0.50
     firm
    -0.47
     che
    -0.47
    POSITIVE LOGITS
     Theſe
    1.00
     Monfieur
    0.94
     pleaſure
    0.91
     myſelf
    0.91
     uſe
    0.90
     ſy
    0.89
     purpoſe
    0.87
     faſt
    0.86
     raiſ
    0.85
     deſt
    0.83
    Activations Density 0.276%

    No Known Activations