© 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. 39854
    Prev
    Next
    INDEX
    Explanations

    ${

    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
    Whilst
    -0.50
     
    -0.48
    amling
    -0.44
     Whilst
    -0.42
    might
    -0.41
     ed
    -0.39
     G
    -0.38
     pre
    -0.38
    нице
    -0.38
    booted
    -0.38
    POSITIVE LOGITS
     <=",
    0.99
    awtextra
    0.96
    uxxxx
    0.95
     Monfieur
    0.92
     Majefty
    0.89
    WriteAttribute
    0.88
     myſelf
    0.86
    fjspx
    0.85
     ſeveral
    0.85
     itſelf
    0.85
    Activations Density 1.099%

    No Known Activations