© 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. 40523
    Prev
    Next
    INDEX
    Explanations

    techniques

    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
     techniques
    -1.53
     practices
    -1.41
     methodologies
    -1.38
     strategies
    -1.33
     methods
    -1.27
     Paglinawan
    -1.23
    techniques
    -1.22
     Techniques
    -1.17
    practices
    -1.17
     concepts
    -1.16
    POSITIVE LOGITS
    .
    0.81
    ,
    0.73
     for
    0.68
     and
    0.67
     of
    0.64
     that
    0.61
     in
    0.59
     used
    0.59
     like
    0.52
     affecting
    0.50
    Activations Density 0.100%

    No Known Activations