© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 1018
    Prev
    Next
    INDEX
    Explanations

    financial figures and dates

    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
     N
    -0.50
     her
    -0.47
     ${\
    -0.46
     van
    -0.44
    i
    -0.43
    ↵↵
    -0.42
     );
    -0.41
     n
    -0.41
     $\
    -0.41
     ta
    -0.41
    POSITIVE LOGITS
     itſelf
    0.90
    itinéraire
    0.87
     myſelf
    0.86
     >=",
    0.84
     ModelExpression
    0.83
    tableFuture
    0.83
     doubtnut
    0.80
    EndGlobalSection
    0.79
     Roskov
    0.79
     Efq
    0.79
    Activations Density 0.914%

    No Known Activations