© 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. 3408
    Prev
    Next
    INDEX
    Explanations

    Sea

    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
     a
    -0.56
     “
    -0.46
     "
    -0.46
    صه
    -0.45
     the
    -0.44
     headed
    -0.44
    rijk
    -0.44
    ائه
    -0.43
    ]}>
    -0.43
     even
    -0.43
    POSITIVE LOGITS
     beginnetje
    0.99
    UnsafeEnabled
    0.90
    EndGlobalSection
    0.84
     Bourgoin
    0.84
    ImageContext
    0.84
     Normdatei
    0.82
    PreferredItem
    0.80
    ViewFeatures
    0.80
     дописавши
    0.79
    <bos>
    0.76
    Activations Density 0.002%

    No Known Activations