© 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. 2559
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
    ]--;
    -0.56
    rogens
    -0.55
    juries
    -0.54
    hObject
    -0.54
     NRW
    -0.52
     porc
    -0.51
    rogen
    -0.51
    anskje
    -0.51
     ChromeDriver
    -0.50
    PhysRev
    -0.50
    POSITIVE LOGITS
     eaters
    0.82
    OGND
    0.66
     about
    0.66
    NameInMap
    0.64
     eater
    0.60
    modelBuilder
    0.56
    Clik
    0.56
    Eating
    0.54
    principalColumn
    0.54
    SearchParams
    0.53
    Activations Density 0.001%

    No Known Activations