© 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. 20-CLT-HP
    7. 75281
    Prev
    Next
    INDEX
    Explanations

    foreign words

    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
    nonatomic
    -0.53
    ="@+
    -0.51
    THRO
    -0.45
     wands
    -0.43
    tro
    -0.41
    ########.
    -0.41
     zon
    -0.41
     zone
    -0.40
    thre
    -0.40
    InitVars
    -0.40
    POSITIVE LOGITS
    kloped
    0.72
    省市镇
    0.59
     correspondingly
    0.59
     ujednoznacz
    0.58
    Cyfeiriadau
    0.57
    DockStyle
    0.57
     sebaliknya
    0.56
    Література
    0.56
     OBITUARY
    0.56
    رشف
    0.55
    Activations Density 0.000%

    No Known Activations