© 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. 11809
    Prev
    Next
    INDEX
    Explanations

    references to hiding or concealing objects

    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
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.79
     defaultstate
    -0.74
    PerformLayout
    -0.60
    Browsable
    -0.59
    ArgsConstructor
    -0.59
     himo
    -0.58
    VersionUID
    -0.57
     <",
    -0.56
    جمعیت
    -0.56
    SequentialGroup
    -0.55
    POSITIVE LOGITS
     undetected
    0.63
     secretly
    0.60
     sneaking
    0.55
     hope
    0.52
    BagLayout
    0.51
    sne
    0.48
     sneak
    0.47
     clandestine
    0.46
     stealth
    0.46
     keber
    0.46
    Activations Density 0.087%

    No Known Activations