© 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. 23523
    Prev
    Next
    INDEX
    Explanations

    positive or strong emotional statements

    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
    brium
    -0.60
     متعلقه
    -0.54
     الاطلاع
    -0.53
     Webber
    -0.51
    MigrationBuilder
    -0.50
     notific
    -0.49
    ρου
    -0.49
     Albert
    -0.48
    marginVertical
    -0.48
    Obra
    -0.48
    POSITIVE LOGITS
     elétrico
    0.64
    closedir
    0.59
    TargetException
    0.59
    saraba
    0.57
    noinspection
    0.56
     محفوظة
    0.56
    formazioni
    0.56
    enerys
    0.56
    ousand
    0.54
     HasFactory
    0.54
    Activations Density 0.069%

    No Known Activations