© 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. 96520
    Prev
    Next
    INDEX
    Explanations

    overcoming limitations

    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
     Chwiliwch
    -0.82
    ⓧ
    -0.82
    Autoritní
    -0.79
    SourceChecksum
    -0.74
     mergeFrom
    -0.71
    MessageOf
    -0.65
     ویکی‌پدی
    -0.63
     utafitiHapana
    -0.63
    لينكات
    -0.63
     Վերցված
    -0.62
    POSITIVE LOGITS
    madre
    0.54
    tableFuture
    0.52
    AttributeSet
    0.49
     Stretch
    0.48
    notin
    0.48
    TestingModule
    0.48
    AndGet
    0.48
     limits
    0.47
    tillon
    0.45
    resave
    0.44
    Activations Density 0.022%

    No Known Activations