© 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. 6514
    Prev
    Next
    INDEX
    Explanations

    phrases related to the feasibility and limitations of creating effective solutions

    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
    rungsseite
    -0.90
     betweenstory
    -0.85
    AndEndTag
    -0.75
    RenderAtEndOf
    -0.74
    AccessorTable
    -0.73
    WithIOException
    -0.71
    aarrggbb
    -0.69
     propOrder
    -0.67
    ThroughAttribute
    -0.66
     AssemblyTitle
    -0.65
    POSITIVE LOGITS
     impossible
    0.76
     невозможно
    0.74
     impossibility
    0.72
     impossível
    0.70
    impossible
    0.69
     cannot
    0.68
    cannot
    0.66
     Cannot
    0.65
    Impossible
    0.61
     unmöglich
    0.60
    Activations Density 0.394%

    No Known Activations