© 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. 10400
    Prev
    Next
    INDEX
    Explanations

    text formatting cues and indicators of continuation or continuation of sentences

    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
    Negative Logits
    findpost
    -0.65
     nakalista
    -0.64
     getRule
    -0.56
     onAnimation
    -0.56
     betweenstory
    -0.54
    RectangleBorder
    -0.54
    __*/
    -0.53
    FieldNumber
    -0.51
    ogramm
    -0.50
     >=",
    -0.50
    POSITIVE LOGITS
     AssemblyCulture
    0.53
    Continue
    0.49
     continuation
    0.48
     Continued
    0.47
    einander
    0.47
     continued
    0.46
    nextElement
    0.45
    áculos
    0.45
    vriende
    0.44
    multi
    0.44
    Activations Density 0.039%

    No Known Activations