© 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. 4257
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
     Itself
    -0.68
     étant
    -0.60
     Either
    -0.58
    tamanya
    -0.57
     vícti
    -0.57
    Either
    -0.57
    ArgsConstructor
    -0.56
     continúas
    -0.56
     ettei
    -0.55
     发表于
    -0.54
    POSITIVE LOGITS
     efforts
    0.66
     programmes
    0.65
     last
    0.63
     recent
    0.63
     programs
    0.56
     attempts
    0.56
     arguments
    0.55
     approaches
    0.53
     measures
    0.53
     concerns
    0.52
    Activations Density 0.001%

    No Known Activations