© 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. 8807
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a specific role or identity, often denoting relationships or positions within a community or context

    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
     metron
    -0.59
    LookAnd
    -0.58
     μετά
    -0.58
    zarchiwizowane
    -0.58
    PreferredItem
    -0.58
     AROUND
    -0.55
     переписи
    -0.54
     turnips
    -0.54
    ométrie
    -0.54
    verläs
    -0.53
    POSITIVE LOGITS
    +#+
    0.59
     pinulongan
    0.57
    
    0.57
     незавершена
    0.55
    principalTable
    0.54
    身为
    0.53
    timeScale
    0.51
    Voci
    0.51
    UnusedPrivate
    0.51
    /***/
    0.50
    Activations Density 0.040%

    No Known Activations