© 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. 901
    Prev
    Next
    INDEX
    Explanations

    code and equations

    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
     تضيفلها
    -0.71
    GraphicsUnit
    -0.68
    TagMode
    -0.68
    GEBURTSDATUM
    -0.65
     nephe
    -0.62
     snippetHide
    -0.61
    Hochspringen
    -0.60
    ()?;
    -0.60
    tonode
    -0.58
     uncin
    -0.57
    POSITIVE LOGITS
    labilir
    0.51
     remercier
    0.46
    werk
    0.43
    ností
    0.43
    Adds
    0.43
     bakom
    0.43
    ivent
    0.42
    Dep
    0.41
     alluminio
    0.41
    legungen
    0.41
    Activations Density 0.009%

    No Known Activations