© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96066
    Prev
    Next
    INDEX
    Explanations

    Technical/research text

    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
     and
    -0.49
    ,
    -0.49
     refugees
    -0.49
     runs
    -0.46
     brethren
    -0.46
    ;
    -0.45
     measures
    -0.45
     supplies
    -0.44
     mistakes
    -0.44
     smells
    -0.43
    POSITIVE LOGITS
    AndEndTag
    1.02
     <>",
    0.94
    oredCriteria
    0.93
    цездатний
    0.88
     propOrder
    0.87
    parsedMessage
    0.79
    featureID
    0.78
    PyExc
    0.75
    +#+#
    0.73
     linkovi
    0.73
    Activations Density 0.001%

    No Known Activations