© 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. 0-CLT-HP
    7. 40335
    Prev
    Next
    INDEX
    Explanations

    discuss

    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
     discussion
    -2.42
    discussion
    -2.14
     discuss
    -2.11
     discussing
    -2.09
    Discussion
    -2.03
     Discussion
    -1.99
     discussed
    -1.93
     discussions
    -1.93
    discuss
    -1.82
     discusses
    -1.81
    POSITIVE LOGITS
     with
    0.79
     the
    0.77
     it
    0.59
     their
    0.58
    JspWriter
    0.58
     our
    0.57
     this
    0.56
     its
    0.55
     any
    0.53
     a
    0.52
    Activations Density 0.505%

    No Known Activations