© 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
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 97722
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     Paglinawan
    -1.06
    expandindo
    -1.03
     workable
    -0.92
    MigrationBuilder
    -0.92
     étoient
    -0.91
     étoit
    -0.89
     auroit
    -0.89
     avoient
    -0.88
    leaved
    -0.87
     myſelf
    -0.87
    POSITIVE LOGITS
     stand
    0.57
     ro
    0.55
     ha
    0.51
    getcwd
    0.51
    defaultValue
    0.49
     pre
    0.47
     pri
    0.47
     har
    0.47
    وا
    0.47
     par
    0.46
    Activations Density 0.066%

    No Known Activations