© 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. 5-CLT-HP
    7. 2886
    Prev
    Next
    INDEX
    Explanations

    "there are"

    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
    <?
    -0.62
    脚注の使い方
    -0.60
     in
    -0.59
     kyse
    -0.59
    тистика
    -0.58
     invokingState
    -0.57
     lanjut
    -0.56
     igjen
    -0.56
    forChild
    -0.56
    berdayakan
    -0.55
    POSITIVE LOGITS
    BindView
    0.49
     onions
    0.47
     rains
    0.46
    ectoria
    0.45
    AddTagHelper
    0.45
    IntentFilter
    0.44
    strates
    0.43
    yw
    0.43
     answers
    0.43
    yt
    0.42
    Activations Density 0.006%

    No Known Activations