© 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. 9842
    Prev
    Next
    INDEX
    Explanations

    academic/scientific texts

    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
     réparation
    -0.54
    Clik
    -0.53
     stratég
    -0.50
    __*/
    -0.47
     esetben
    -0.46
     Vir
    -0.45
    DialogInterface
    -0.44
    waitKey
    -0.43
     diversité
    -0.43
    StackNavigator
    -0.43
    POSITIVE LOGITS
     aidant
    0.63
     AFS
    0.62
    ViewFeatures
    0.62
    EDEFAULT
    0.61
     spade
    0.60
     hObject
    0.60
    Tembelea
    0.60
    mobileqq
    0.59
    ]));
    0.58
     CSM
    0.58
    Activations Density 0.016%

    No Known Activations