© 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. 4204
    Prev
    Next
    INDEX
    Explanations

    colons, numbers, or website context

    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
    '}>
    -0.65
    rawDesc
    -0.64
    `]
    -0.64
    Портал
    -0.63
    ]").
    -0.62
    曖昧さ回避
    -0.62
    >");
    -0.60
    Autoritní
    -0.60
    '},
    -0.60
    %"),
    -0.59
    POSITIVE LOGITS
     surla
    0.47
    صیلات
    0.47
    RegistryLite
    0.45
     Wicidata
    0.45
    Jîn
    0.43
    StoryboardSegue
    0.42
    clusão
    0.41
    GZIP
    0.39
    المناصب
    0.38
    GraphicsUnit
    0.38
    Activations Density 0.000%

    No Known Activations