© 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. 0-CLT-HP
    4. 39966
    Prev
    Next
    INDEX
    Explanations

    broiler

    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
     للمعارف
    -0.98
     parlé
    -0.66
     apologies
    -0.63
    GraphicsUnit
    -0.62
    setViewportView
    -0.62
     blessé
    -0.60
    docx
    -0.59
     déclar
    -0.55
    RTEE
    -0.54
     متعلقه
    -0.51
    POSITIVE LOGITS
    oodoo
    0.57
    cedure
    0.53
     vững
    0.50
    tomie
    0.49
    warma
    0.48
    aktur
    0.48
     God
    0.48
    uffff
    0.47
    nambuco
    0.47
    RITION
    0.47
    Activations Density 1.311%

    No Known Activations