© 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. 42358
    Prev
    Next
    INDEX
    Explanations

    When

    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
     Houſe
    -1.24
     pleaſure
    -1.16
     Anſ
    -1.11
     itſelf
    -1.08
    ſelf
    -1.05
     Reſ
    -1.03
     houſe
    -1.02
     myſelf
    -1.00
     Diſ
    -1.00
     uſe
    -0.99
    POSITIVE LOGITS
     you
    1.27
     it
    1.16
     I
    1.10
     we
    1.10
     he
    0.91
     they
    0.85
     my
    0.79
     your
    0.77
     a
    0.75
     the
    0.75
    Activations Density 0.065%

    No Known Activations