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. 796
    Prev
    Next
    INDEX
    Explanations

    End

    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
    (
    -0.41
    pr
    -0.41
    ho
    -0.40
    semp
    -0.40
    osp
    -0.39
    nu
    -0.38
    er
    -0.38
     instance
    -0.38
     שוליים
    -0.37
    for
    -0.37
    POSITIVE LOGITS
     vectorielles
    0.95
    Tikang
    0.89
     normaux
    0.85
     fermés
    0.85
     avoient
    0.84
     мәкал
    0.84
     démocr
    0.84
    sofá
    0.81
     financières
    0.80
     colorés
    0.77
    Activations Density 0.233%

    No Known Activations