© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93081
    Prev
    Next
    INDEX
    Explanations

    urban density

    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
     världen
    -0.54
     fatica
    -0.50
    Workshop
    -0.49
     alimentaire
    -0.48
    Bathrooms
    -0.47
     autorités
    -0.47
     <<<<<<<<<<<<<<
    -0.47
     pères
    -0.47
     détermination
    -0.46
    NOPQRST
    -0.46
    POSITIVE LOGITS
     development
    0.67
    ly
    0.64
    AxisAlignment
    0.61
     developments
    0.61
    ConstraintMaker
    0.58
    енча
    0.53
    LY
    0.53
    ReusableCell
    0.50
     construction
    0.49
    complexContent
    0.49
    Activations Density 0.002%

    No Known Activations