© 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. 91946
    Prev
    Next
    INDEX
    Explanations

    multimedia

    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
     Monfieur
    -1.15
     purpoſe
    -1.10
     myſelf
    -1.10
     enfans
    -1.08
    følgelig
    -1.05
     auffi
    -1.05
    ſelves
    -1.03
     Anſ
    -1.03
     themſelves
    -1.02
     auroit
    -1.00
    POSITIVE LOGITS
     som
    0.60
    ↵
    0.57
     B
    0.56
    ↵↵
    0.54
     d
    0.54
     der
    0.52
     Som
    0.51
     da
    0.51
     «
    0.50
     
    0.50
    Activations Density 0.118%

    No Known Activations