© 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. 95005
    Prev
    Next
    INDEX
    Explanations

    Beginning of a text

    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
     Theſe
    -0.77
     Houſe
    -0.75
     myſelf
    -0.73
     Eſ
    -0.73
     Efq
    -0.72
     becauſe
    -0.71
     Anſ
    -0.71
     houſe
    -0.71
     itſelf
    -0.71
     unſ
    -0.70
    POSITIVE LOGITS
     StatelessWidget
    0.71
    ennium
    0.58
     Bioaccumulative
    0.53
     StatefulWidget
    0.52
    NewUrlParser
    0.51
    Jereo
    0.50
     City
    0.49
     aient
    0.48
    rifugal
    0.47
     pres
    0.47
    Activations Density 1.212%

    No Known Activations