Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 0-CLT-HP
    4. 91746
    Prev
    Next
    INDEX
    Explanations

    resin

    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
     Expense
    -0.44
     expense
    -0.44
     enda
    -0.44
    ní
    -0.42
     Muss
    -0.42
     Wunsch
    -0.41
     varm
    -0.41
    Li
    -0.40
    ्य
    -0.40
    おり
    -0.39
    POSITIVE LOGITS
    SBATCH
    0.93
     whoſe
    0.84
     Theſe
    0.82
     ſind
    0.79
    вгений
    0.77
     myſelf
    0.77
     themſelves
    0.76
     HasFactory
    0.75
     Efq
    0.75
     itſelf
    0.75
    Activations Density 1.715%

    No Known Activations