© 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. 44058
    Prev
    Next
    INDEX
    Explanations

    academic/scientific contexts

    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
     Cæsar
    -0.94
     Houſe
    -0.90
     ainfi
    -0.90
     Shakspeare
    -0.82
     Tacitus
    -0.81
     auffi
    -0.79
     réduite
    -0.78
     plufieurs
    -0.78
     photolibrary
    -0.77
     Diſ
    -0.77
    POSITIVE LOGITS
    gun
    0.64
     the
    0.60
    book
    0.60
     for
    0.58
    lander
    0.57
    door
    0.57
    wire
    0.56
     a
    0.56
     at
    0.56
     Har
    0.56
    Activations Density 1.568%

    No Known Activations