© 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. 32046
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming

    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
    enumii
    -0.94
    ագրություններ
    -0.91
    enumi
    -0.88
     rospy
    -0.85
    fromCharCode
    -0.81
    oplayer
    -0.79
     utafitiHapana
    -0.77
     يتيمه
    -0.77
     grs
    -0.77
    )("
    -0.76
    POSITIVE LOGITS
    </em>
    0.64
    </blockquote>
    0.60
    ,
    0.57
     
    0.56
    RIN
    0.55
    ↵
    0.53
    kede
    0.51
    using
    0.51
    0.51
     Min
    0.50
    Activations Density 0.007%
    No Known Activations