© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 1690
    Prev
    Next
    INDEX
    Explanations

    phrases indicating relationships or connections between entities

    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
     pleaſure
    -0.71
     Hecht
    -0.69
     fhort
    -0.67
     Myra
    -0.67
     total
    -0.66
    nada
    -0.66
     cay
    -0.63
    `<
    -0.62
     Efq
    -0.62
     PDA
    -0.61
    POSITIVE LOGITS
    clerosis
    0.76
    ApiProperty
    0.75
    +#+#
    0.75
     Normdatei
    0.74
     consultato
    0.73
    ReusableCell
    0.73
     BoxDecoration
    0.72
    aarrggbb
    0.72
     Amongst
    0.71
    __(/*!
    0.69
    Activations Density 0.779%

    No Known Activations