© 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. 679
    Prev
    Next
    INDEX
    Explanations

    Dates and numbers

    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
    AsUp
    -0.75
    Tikang
    -0.72
    PreferredItem
    -0.69
    __":
    -0.67
    bootstrapcdn
    -0.66
    __':
    -0.65
    __':
    -0.65
    featureID
    -0.65
    Приложение
    -0.64
     تانيه
    -0.64
    POSITIVE LOGITS
    -
    0.51
    /
    0.45
    –
    0.44
     by
    0.43
    <bos>
    0.40
     ModelRenderer
    0.40
    Δ
    0.39
    че
    0.38
     Zeug
    0.36
    CommandText
    0.36
    Activations Density 0.004%

    No Known Activations