Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 73714
    Prev
    Next
    INDEX
    Explanations

    half

    np_max-act-logits · 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
     réguli
    -0.47
     henvisninger
    -0.45
     fermés
    -0.44
     ComVisible
    -0.44
    %)$
    -0.43
    
    -0.42
     véritables
    -0.42
    ]]);
    -0.41
    infan
    -0.41
    neté
    -0.40
    POSITIVE LOGITS
    Half
    0.91
     half
    0.89
     Half
    0.87
    half
    0.82
     Efq
    0.77
    HALF
    0.77
     fhew
    0.75
     myſelf
    0.75
     HALF
    0.74
     Majefty
    0.74
    Activations Density 0.040%

    No Known Activations