© 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. 45159
    Prev
    Next
    INDEX
    Explanations

    yellow

    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
     yellow
    -1.37
    Yellow
    -1.22
     Yellow
    -1.16
    yellow
    -1.12
     yellows
    -1.05
     YELLOW
    -0.96
     amarillo
    -0.90
    marked
    -0.88
     jaune
    -0.88
     amarelo
    -0.87
    POSITIVE LOGITS
     bru
    0.51
    rande
    0.49
    hynchus
    0.49
     Mile
    0.47
    Cruel
    0.47
     mig
    0.45
    ترت
    0.45
     star
    0.45
     vis
    0.44
    tgz
    0.44
    Activations Density 0.145%

    No Known Activations