© 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. 17095
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and hyphens

    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
    Personensuche
    -1.30
     Мексичка
    -1.16
    InjectAttribute
    -1.12
    Personendaten
    -1.09
     betweenstory
    -1.05
    ScopeManager
    -1.01
    WriteTagHelper
    -0.97
     فريبيس
    -0.96
    principalTable
    -0.96
     defaultstate
    -0.95
    POSITIVE LOGITS
     tu
    0.49
    цар
    0.47
     She
    0.45
    sib
    0.45
     {$
    0.44
    ########
    0.43
    stof
    0.43
     I
    0.43
    hem
    0.43
    {$
    0.42
    Activations Density 0.024%

    No Known Activations