© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96944
    Prev
    Next
    INDEX
    Explanations

    s

    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
     getItemCount
    -0.47
    ัติ
    -0.45
     nahilalakip
    -0.44
     world
    -0.44
    ]));
    -0.43
    Портал
    -0.42
    hael
    -0.41
    ਹ
    -0.41
    )));
    -0.41
    world
    -0.41
    POSITIVE LOGITS
     Савезне
    0.63
     prettiest
    0.63
    TestingModule
    0.61
     volcanoes
    0.59
    IContainer
    0.58
     greateſt
    0.58
    IVersion
    0.57
    σθαι
    0.57
     counties
    0.56
    IntoConstraints
    0.55
    Activations Density 0.002%

    No Known Activations