© 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. 5-CLT-HP
    7. 98136
    Prev
    Next
    INDEX
    Explanations

    cultures

    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
    IsContent
    -0.56
    lapsingToolbar
    -0.56
    DockStyle
    -0.52
    Geplaatst
    -0.52
    })`
    -0.51
    ="#"><
    -0.50
     Roskov
    -0.48
     “...
    -0.48
     accro
    -0.48
    ToScroll
    -0.48
    POSITIVE LOGITS
     [*]
    0.55
     used
    0.49
     loss
    0.49
     serving
    0.49
    FieldBuilder
    0.48
     acting
    0.47
    ี่ยม
    0.47
    ربعة
    0.47
     sin
    0.47
    обы
    0.47
    Activations Density 0.000%

    No Known Activations