© 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. 4-CLT-HP
    7. 2227
    Prev
    Next
    INDEX
    Explanations

    describing processes

    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
    edoc
    -0.46
    честву
    -0.44
    EReference
    -0.41
    στό
    -0.41
     Könige
    -0.40
     eccl
    -0.39
     correlations
    -0.39
    toso
    -0.38
     Gemeinschaft
    -0.38
    astéroïdes
    -0.38
    POSITIVE LOGITS
    <bos>
    1.23
    Tikang
    1.00
    OGND
    0.96
    +#+#
    0.84
    findpost
    0.82
    RTEE
    0.81
     autorytatywna
    0.81
     AssemblyCulture
    0.79
     cherchés
    0.79
     noDo
    0.77
    Activations Density 0.007%

    No Known Activations