© 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. 4-CLT-HP
    7. 4512
    Prev
    Next
    INDEX
    Explanations

    angles and direction

    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
    rouse
    -0.60
     himſelf
    -0.52
    енча
    -0.52
    layer
    -0.51
    cosystem
    -0.49
    entera
    -0.48
     Chriftian
    -0.48
    LAY
    -0.48
    actéris
    -0.48
     themſelves
    -0.47
    POSITIVE LOGITS
     of
    0.77
    ality
    0.59
     disambiguazione
    0.58
     directions
    0.57
    principalTable
    0.57
    icism
    0.54
     direction
    0.51
    ism
    0.50
     ComVisible
    0.50
     pull
    0.50
    Activations Density 0.001%

    No Known Activations