© 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. 24750
    Prev
    Next
    INDEX
    Explanations

    elements of a structured data representation, such as graphs or nodes

    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
    StoryboardSegue
    -0.65
     BitmapFactory
    -0.58
     TPE
    -0.57
     initWithFrame
    -0.57
     UITextField
    -0.56
     AssertionError
    -0.56
     Rubens
    -0.55
     FileWriter
    -0.55
     '\''
    -0.55
    LLocation
    -0.54
    POSITIVE LOGITS
    ⓧ
    0.83
    
    0.67
     uska
    0.62
    }))
    0.62
    LookAnd
    0.60
    )))))
    0.60
    Personensuche
    0.59
    rawDesc
    0.58
    ="#"><
    0.56
     ligiloj
    0.55
    Activations Density 0.037%

    No Known Activations