© 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. 5-CLT-HP
    4. 3273
    Prev
    Next
    INDEX
    Explanations

    period

    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
    ########.
    -0.83
    setVerticalGroup
    -0.81
     @"/
    -0.71
     onAnimation
    -0.69
     betweenstory
    -0.69
     extermination
    -0.67
    Rhestr
    -0.66
    DIPSETTING
    -0.66
     étoit
    -0.66
     Shuk
    -0.66
    POSITIVE LOGITS
     based
    0.59
     ...
    0.56
    Finally
    0.54
    The
    0.50
     in
    0.50
    A
    0.49
     he
    0.49
     the
    0.48
     after
    0.48
     next
    0.47
    Activations Density 0.014%

    No Known Activations