© 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. 96051
    Prev
    Next
    INDEX
    Explanations

    written articles

    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
    ynchronously
    -0.69
    :]:
    -0.68
    SequentialGroup
    -0.66
    Życiorys
    -0.65
     EconPapers
    -0.64
    ﷺ
    -0.64
     estekak
    -0.63
    PerformLayout
    -0.61
    ngOnInit
    -0.60
    )))));
    -0.59
    POSITIVE LOGITS
     it
    0.76
     there
    0.64
     rêver
    0.57
    there
    0.51
    rsiniz
    0.50
     rire
    0.48
     esso
    0.46
    ешься
    0.46
     hoek
    0.46
    Pautan
    0.45
    Activations Density 0.003%

    No Known Activations