© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15466
    Prev
    Next
    INDEX
    Explanations

    instances of the word "currently."

    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
    bion
    -0.62
    dressing
    -0.59
    rews
    -0.58
     now
    -0.57
     Obec
    -0.57
     current
    -0.55
     NOW
    -0.55
    Sow
    -0.55
    раздо
    -0.54
     today
    -0.53
    POSITIVE LOGITS
    AnchorStyles
    0.85
    GenerationType
    0.84
    RetentionPolicy
    0.84
    expandindo
    0.83
    JvmStatic
    0.82
     Majefty
    0.81
    UnusedPrivate
    0.77
     Diſ
    0.77
     Schulte
    0.75
    abestanden
    0.75
    Activations Density 0.013%

    No Known Activations