© 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. 20099
    Prev
    Next
    INDEX
    Explanations

    frequencies and measurements related to time or date

    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
     Theſe
    -0.81
     lenker
    -0.75
    SourceChecksum
    -0.66
     Anſ
    -0.66
     Beſ
    -0.65
    XmlAccessorType
    -0.64
    PostExecute
    -0.62
    ERÍA
    -0.62
    gameserver
    -0.61
    xFFFFFF
    -0.61
    POSITIVE LOGITS
    __':
    0.64
    endpush
    0.59
     ái
    0.57
     javafx
    0.54
     acacia
    0.53
    createClass
    0.52
     misto
    0.51
    }));
    0.50
     Dilemma
    0.50
    </blockquote>
    0.49
    Activations Density 0.059%

    No Known Activations