© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 77535
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act-logits · 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
     supérieurs
    -0.70
     judiciales
    -0.66
    vellous
    -0.62
    predator
    -0.60
    ABAJO
    -0.58
    tilt
    -0.57
    יצוני
    -0.57
    APPRO
    -0.57
     jspb
    -0.57
     -->>
    -0.57
    POSITIVE LOGITS
     kasarigan
    0.66
    createObject
    0.54
     compri
    0.53
    resave
    0.47
     tắc
    0.47
     cut
    0.45
    Népesség
    0.44
     feeling
    0.43
     vedette
    0.43
    boxShadow
    0.42
    Activations Density 0.001%

    No Known Activations