© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 841
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups identified as "a" followed by notable descriptors, often conveying a sense of personality or status

    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
    #+#
    -0.86
    WriteBarrier
    -0.77
    AddTagHelper
    -0.75
    eseed
    -0.74
    Vidite
    -0.71
     PublicKey
    -0.69
     CanadaChoose
    -0.68
    SourceChecksum
    -0.67
     CURIAM
    -0.66
    IUrlHelper
    -0.66
    POSITIVE LOGITS
    endphp
    0.59
     发表于
    0.56
    /*.
    0.53
     very
    0.52
     whiteColor
    0.52
    epro
    0.52
    ργο
    0.52
     Very
    0.50
     quite
    0.49
    VERY
    0.49
    Activations Density 0.476%

    No Known Activations