© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    references to cylindrical shapes or structures

    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
    TargetException
    -0.71
    AnimationFrame
    -0.67
     Bona
    -0.66
    isance
    -0.65
     län
    -0.64
    vogel
    -0.64
    apeake
    -0.64
     vuotta
    -0.63
    sint
    -0.63
     packageName
    -0.63
    POSITIVE LOGITS
    indrical
    1.46
     cylindrical
    1.37
    cyl
    1.22
     cylinders
    1.22
     cylinder
    1.19
     cylind
    1.15
    cylinder
    1.15
     Cyl
    1.14
    Cyl
    1.06
     cilind
    1.04
    Activations Density 0.003%

    No Known Activations