© 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. 23236
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "like" 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
     برانيه
    -0.58
    ритори
    -0.57
    neider
    -0.56
    Aquila
    -0.56
    ───
    -0.55
    pecific
    -0.55
     inter
    -0.54
    ually
    -0.54
    -------------</
    -0.53
     mendatang
    -0.53
    POSITIVE LOGITS
    LookAnd
    0.68
     HasFactory
    0.60
    âtre
    0.58
    AutoScaleMode
    0.58
    EDEFAULT
    0.58
     Torrance
    0.57
     TextStyle
    0.55
     Detected
    0.55
    uerdo
    0.55
     viewDidLoad
    0.55
    Activations Density 0.030%

    No Known Activations