© 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. 5-CLT-HP
    4. 95224
    Prev
    Next
    INDEX
    Explanations

    how

    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
     wireType
    -0.63
    
    -0.61
    uxxxx
    -0.60
    WebVitals
    -0.60
    таратура
    -0.59
    rungsseite
    -0.59
    alisme
    -0.58
    HasForeignKey
    -0.58
     kasarigan
    -0.57
     
    -0.56
    POSITIVE LOGITS
     it
    1.05
     that
    0.84
     to
    0.72
     this
    0.56
    GOTREF
    0.53
     abzu
    0.49
    that
    0.48
    それは
    0.47
     its
    0.47
     auszu
    0.47
    Activations Density 0.000%

    No Known Activations