© 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. 5-CLT-HP
    4. 2056
    Prev
    Next
    INDEX
    Explanations

    foreign languages

    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
     this
    -1.09
    this
    -0.96
     này
    -0.85
     This
    -0.80
     these
    -0.79
     dette
    -0.78
     THIS
    -0.78
     detta
    -0.75
     этого
    -0.74
     THESE
    -0.71
    POSITIVE LOGITS
     nahilalakip
    0.55
     FetchType
    0.54
    fortawesome
    0.53
     InputDecoration
    0.51
    URLException
    0.50
    脚注の使い方
    0.50
    avits
    0.48
    Brainz
    0.48
     RTS
    0.46
     IBOutlet
    0.45
    Activations Density 0.004%

    No Known Activations