© 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. 94886
    Prev
    Next
    INDEX
    Explanations

    numerical quantities

    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
    SequentialGroup
    -0.75
    PerformLayout
    -0.73
     مشين
    -0.65
     poffe
    -0.63
    kloped
    -0.63
    MessageOf
    -0.62
    AndEndTag
    -0.61
    Personensuche
    -0.60
    queryInterface
    -0.60
    LookAnd
    -0.60
    POSITIVE LOGITS
    isor
    0.52
    kits
    0.43
    kicks
    0.43
    chants
    0.43
    cuts
    0.42
    writer
    0.42
    lids
    0.42
    skis
    0.41
    ]),
    0.41
    iour
    0.41
    Activations Density 0.002%

    No Known Activations