© 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. 902
    Prev
    Next
    INDEX
    Explanations

    asthma

    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
     podjela
    -0.52
    角
    -0.52
    rotnie
    -0.44
    Mixtures
    -0.44
    endola
    -0.42
    ιδ
    -0.42
    ze
    -0.42
    <bos>
    -0.42
     integrand
    -0.42
     بزر
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.92
     Chwiliwch
    0.74
    MemoryWarning
    0.74
    GraphicsUnit
    0.71
    ChildScrollView
    0.68
    MigrationBuilder
    0.66
    Tikang
    0.65
    isticated
    0.63
     AsyncTask
    0.60
    évaluateur
    0.59
    Activations Density 0.001%

    No Known Activations