© 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. 20-CLT-HP
    7. 72127
    Prev
    Next
    INDEX
    Explanations

    animal

    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
     kasarigan
    -0.91
    DeleteBehavior
    -0.70
    tonode
    -0.69
     initComponents
    -0.66
     Obrador
    -0.64
     disambiguazione
    -0.63
    ExecuteReader
    -0.61
     nonatomic
    -0.60
    didSet
    -0.60
     intptr
    -0.60
    POSITIVE LOGITS
    cul
    0.58
    cu
    0.46
    巅
    0.45
    ia
    0.44
    culi
    0.43
    omor
    0.42
    cla
    0.41
    illi
    0.41
    veg
    0.41
    COOKIE
    0.40
    Activations Density 0.002%

    No Known Activations