© 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. 45211
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
     hearing
    -0.65
    EndProject
    -0.62
     Jumper
    -0.56
    phalt
    -0.55
    hearing
    -0.55
    complexType
    -0.54
     AssemblyTitle
    -0.54
    Démographie
    -0.53
    s
    -0.53
     Italijani
    -0.53
    POSITIVE LOGITS
    tymologie
    0.63
     syke
    0.61
     pernas
    0.59
    råd
    0.57
    føring
    0.57
    AddField
    0.56
     igjen
    0.54
    greenrobot
    0.54
    sidemargin
    0.54
    fører
    0.53
    Activations Density 0.155%

    No Known Activations