© 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. 4-CLT-HP
    7. 396
    Prev
    Next
    INDEX
    Explanations

    exceptions

    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
    ReusableCell
    -0.70
    </caption>
    -0.69
    ſelf
    -0.66
     eenige
    -0.59
     Theſe
    -0.58
    ſelves
    -0.56
    bewerken
    -0.56
     esimer
    -0.56
     Himo
    -0.54
     plads
    -0.54
    POSITIVE LOGITS
     I
    1.21
     if
    0.97
     we
    0.93
     there
    0.84
     they
    0.81
     it
    0.77
     don
    0.77
     whereas
    0.75
     maybe
    0.69
     he
    0.69
    Activations Density 0.007%

    No Known Activations