© 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. 45293
    Prev
    Next
    INDEX
    Explanations

    Public service

    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
     mean
    -0.80
    saraba
    -0.60
    ISupport
    -0.59
    رشف
    -0.56
     snippetHide
    -0.56
    cos
    -0.52
    mean
    -0.51
     about
    -0.48
    PRNewswire
    -0.47
     LOT
    -0.46
    POSITIVE LOGITS
     esternos
    0.83
     Houſe
    0.79
     houſe
    0.75
     Cæsar
    0.70
     pleaſure
    0.70
     Reſ
    0.65
     Jefus
    0.64
     Efq
    0.62
     unſ
    0.62
     ſche
    0.62
    Activations Density 0.032%

    No Known Activations