© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "unlocking."

    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
     isComment
    -0.67
    ObjectContext
    -0.61
    AuthContext
    -0.60
     yii
    -0.59
    parsedMessage
    -0.57
    RegisterType
    -0.57
     Cindy
    -0.55
    scriptId
    -0.54
    Zin
    -0.52
    Rout
    -0.52
    POSITIVE LOGITS
    unlock
    1.10
    Unlock
    0.92
     Unlock
    0.85
     unlock
    0.84
     unlocks
    0.78
     unlocked
    0.77
     unlocking
    0.75
     desbloquear
    0.75
    UNLOCK
    0.74
     desblo
    0.72
    Activations Density 0.000%

    No Known Activations