© 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. 0-CLT-HP
    7. 38850
    Prev
    Next
    INDEX
    Explanations

    technical content

    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
     er
    -1.74
     Er
    -1.35
    Er
    -1.08
     nakalista
    -0.82
    IsContent
    -0.79
    +#+
    -0.76
    aarrggbb
    -0.75
     propOrder
    -0.71
    tagHelperRunner
    -0.70
    MethodManager
    -0.70
    POSITIVE LOGITS
     Shaksp
    0.59
     Shakspeare
    0.57
     näytte
    0.53
     coppia
    0.52
     elä
    0.51
     dumne
    0.51
    ging
    0.51
     azioni
    0.51
     lobes
    0.50
     traduzione
    0.50
    Activations Density 0.106%

    No Known Activations