© 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. 12-RES-MATRYOSHKA-DC
    4. 19244
    Prev
    Next
    INDEX
    Explanations

    URLs and references to online resources

    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
    Portail
    -0.82
     Monfieur
    -0.77
     pinulongan
    -0.75
     Majefty
    -0.71
     defStyleAttr
    -0.68
     Anſ
    -0.68
     متعلقه
    -0.67
     Houſe
    -0.66
    IonicModule
    -0.66
     Perſ
    -0.65
    POSITIVE LOGITS
     Se
    0.55
    ']],
    0.55
    ENDE
    0.52
     ?>>
    0.52
    率
    0.52
    IEVE
    0.51
    yves
    0.51
    $',
    0.50
    dele
    0.50
    ;'>
    0.50
    Activations Density 0.008%

    No Known Activations