© 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. 18-RES-MATRYOSHKA-DC
    7. 1065
    Prev
    Next
    INDEX
    Explanations

    dates and information about the current time.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     later
    -1.16
     später
    -1.07
     earlier
    -1.06
     senere
    -1.03
    later
    -1.02
     później
    -1.02
     wcześniej
    -0.98
    当時は
    -0.98
    earlier
    -0.95
     afterwards
    -0.94
    POSITIVE LOGITS
     becomes
    0.69
    again
    0.67
     again
    0.66
     finally
    0.66
     suddenly
    0.65
     became
    0.64
     announced
    0.64
     endlich
    0.61
     enfin
    0.61
     наконец
    0.59
    Activations Density 1.887%

    No Known Activations