© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 18627
    Prev
    Next
    INDEX
    Explanations

    phrases related to timeframes and specific periods

    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
     OFDb
    -0.77
     '\\;'
    -0.77
    TagMode
    -0.76
     propOrder
    -0.74
    })));
    -0.65
     CreateTagHelper
    -0.64
    principalColumn
    -0.64
     defaultstate
    -0.60
    SequentialGroup
    -0.59
    contentLoaded
    -0.59
    POSITIVE LOGITS
     виправивши
    0.53
    ilarities
    0.51
     tombé
    0.49
    uality
    0.49
     καν
    0.47
    IANGLES
    0.47
     wholes
    0.46
     internetowa
    0.46
     indisponible
    0.46
    InitStruct
    0.45
    Activations Density 0.014%

    No Known Activations