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. 12-RES-MATRYOSHKA-DC
    4. 14681
    Prev
    Next
    INDEX
    Explanations

    content related to statistical measures and clinical trial data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ―――――
    -0.77
     itſelf
    -0.68
     Theſe
    -0.68
    SourceChecksum
    -0.66
     Autorizaciones
    -0.66
     Мексичка
    -0.64
    StoryboardSegue
    -0.63
     חיצוניים
    -0.62
     ་་
    -0.62
    ')")
    -0.62
    POSITIVE LOGITS
     puntata
    0.54
     garanzia
    0.53
    
    0.52
     I
    0.52
     Protección
    0.52
     alluminio
    0.52
     deberes
    0.51
     المعيارى
    0.48
    +#+#
    0.47
     skydd
    0.47
    Activations Density 0.089%

    No Known Activations