Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 44272
    Prev
    Next
    INDEX
    Explanations

    design and technology

    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
     feroit
    -1.45
     avoient
    -1.36
     pouvoit
    -1.36
     étoient
    -1.34
     crdi
    -1.34
     auroit
    -1.31
     ainfi
    -1.29
     plufieurs
    -1.27
    <pad>
    -1.27
    [@BOS@]
    -1.27
    POSITIVE LOGITS
    .
    1.23
    ,
    1.22
     of
    1.13
     (
    1.11
     and
    1.10
    '
    1.09
    ed
    1.09
     
    1.09
     for
    1.08
    -
    1.08
    Activations Density 0.125%

    No Known Activations