© 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. 9626
    Prev
    Next
    INDEX
    Explanations

    digital signatures/policies

    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
     démocr
    -0.66
    niająca
    -0.65
     refroid
    -0.65
     chré
    -0.64
     culturelle
    -0.62
     fermés
    -0.61
     régl
    -0.60
     scolaires
    -0.60
    sejarah
    -0.60
     giusti
    -0.59
    POSITIVE LOGITS
    2
    0.54
    AutoField
    0.49
     ante
    0.47
     key
    0.46
    NameInMap
    0.46
    oa̍t
    0.46
    1
    0.45
    stateProvider
    0.45
    ReusableCell
    0.45
     C
    0.44
    Activations Density 0.239%

    No Known Activations