© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 43758
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    ſelves
    -1.00
     Shakspeare
    -1.00
    neſs
    -0.99
     Houſe
    -0.98
     Efq
    -0.97
     myſelf
    -0.97
     Theſe
    -0.95
     Conſ
    -0.94
    ſelf
    -0.92
     Monfieur
    -0.91
    POSITIVE LOGITS
     du
    0.45
     and
    0.44
     trans
    0.42
     es
    0.41
     vo
    0.40
     her
    0.39
     n
    0.38
    EDEFAULT
    0.38
     scratch
    0.38
     dire
    0.37
    Activations Density 0.169%

    No Known Activations