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. 25538
    Prev
    Next
    INDEX
    Explanations

    references to scientific publications and journal articles

    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
     विश्वसनीयता
    -0.79
    ();)
    -0.74
    });*/
    -0.73
    edicated
    -0.69
    ########.
    -0.68
    }")
    
    -0.68
    //});
    -0.67
    ecore
    -0.67
     dynasties
    -0.67
     الرياضيه
    -0.66
    POSITIVE LOGITS
     saites
    0.54
    :✨
    0.52
     D
    0.50
     <<<<<<<<<<<<<<
    0.47
     presente
    0.45
     intptr
    0.45
     parcela
    0.44
    PreferredItem
    0.43
     &___
    0.43
    InSection
    0.42
    Activations Density 0.001%

    No Known Activations