© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 2319
    Prev
    Next
    INDEX
    Explanations

    dog

    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
     dog
    -0.60
    GEBURTSDATUM
    -0.50
     child
    -0.43
    ANNES
    -0.43
    getLogger
    -0.43
     immuno
    -0.41
     puppy
    -0.40
     dogs
    -0.40
     nog
    -0.40
    Chico
    -0.40
    POSITIVE LOGITS
    IsPostBack
    0.73
    igshid
    0.69
    kháu
    0.65
     AttributeSet
    0.65
    ViewInit
    0.62
    TestingModule
    0.61
    LocationManager
    0.58
    \{\\
    0.58
    lorette
    0.57
    __.__
    0.56
    Activations Density 0.002%

    No Known Activations