© 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. 1-CLT-HP
    7. 9701
    Prev
    Next
    INDEX
    Explanations

    in

    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
    "])
    -0.62
     defaultstate
    -0.61
    Personendaten
    -0.59
    ervlak
    -0.58
     sherds
    -0.57
    ReusableCell
    -0.56
     kaarangay
    -0.54
    addCriterion
    -0.54
    WebVitals
    -0.53
     transfieras
    -0.53
    POSITIVE LOGITS
     käyttö
    0.53
     laikā
    0.51
     avulla
    0.50
    dirkan
    0.49
     use
    0.48
    Portail
    0.47
     trekken
    0.47
     mendatang
    0.45
     wacht
    0.45
     place
    0.45
    Activations Density 0.065%

    No Known Activations