© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    vitro

    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
    Cooking
    -0.59
     respects
    -0.58
     Cooking
    -0.57
    cooking
    -0.55
     cook
    -0.53
     vitro
    -0.53
     cooking
    -0.52
     cocinar
    -0.49
     nélk
    -0.47
    cook
    -0.46
    POSITIVE LOGITS
    Билгалдахарш
    0.97
     pinulongan
    0.91
    Personendaten
    0.88
    SharedDtor
    0.88
     InputDecoration
    0.86
    NUMX
    0.85
    audiovisuel
    0.85
    脚注の使い方
    0.84
    دانشنامهٔ
    0.83
     propOrder
    0.83
    Activations Density 0.538%

    No Known Activations