© 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. 30713
    Prev
    Next
    INDEX
    Explanations

    words related to anchoring or connection in various contexts

    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
    اض
    -0.76
    cticut
    -0.74
     Scy
    -0.71
    RemoteException
    -0.71
     Syrie
    -0.69
    Tanya
    -0.68
     Vicenza
    -0.68
     Gothenburg
    -0.67
     ADS
    -0.66
     Byd
    -0.66
    POSITIVE LOGITS
     anchor
    1.80
     anchors
    1.76
     Anchor
    1.70
    anchors
    1.68
    anchor
    1.66
    Anchor
    1.49
    CHOR
    1.46
     Anch
    1.45
     anchoring
    1.38
     anchored
    1.34
    Activations Density 0.002%

    No Known Activations