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. 24471
    Prev
    Next
    INDEX
    Explanations

    references to virtual components or systems

    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
    bson
    -0.72
     OnInit
    -0.72
     modi
    -0.70
     jedis
    -0.68
     Changelog
    -0.68
     coreana
    -0.66
     Goy
    -0.65
     Nade
    -0.65
     venons
    -0.65
     Caballero
    -0.64
    POSITIVE LOGITS
     VIRTUAL
    1.01
     Virtual
    0.96
    Virtual
    0.96
    VIRTUAL
    0.93
    virtual
    0.92
     virtual
    0.90
    躇
    0.78
     Virtu
    0.78
    VIAF
    0.75
     virtuel
    0.73
    Activations Density 0.005%

    No Known Activations