© 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. 44201
    Prev
    Next
    INDEX
    Explanations

    code

    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
    letal
    -1.02
    anyika
    -0.95
     Belmont
    -0.55
    chism
    -0.51
    y
    -0.51
    }*/
    
    -0.49
    sta
    -0.49
     ujednoznacz
    -0.48
    AutoScale
    -0.47
     M
    -0.47
    POSITIVE LOGITS
     itſelf
    0.88
     Houſe
    0.84
     Jefus
    0.82
     poffible
    0.79
     pleaſure
    0.78
     Reſ
    0.76
     themſelves
    0.74
     myſelf
    0.73
     scania
    0.73
     pleaf
    0.72
    Activations Density 0.036%

    No Known Activations