© 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
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 32211
    Prev
    Next
    INDEX
    Explanations

    quotation marks and dialogue expressions

    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
    帖最后由
    -0.91
    XmlAccessType
    -0.79
    aarrggbb
    -0.70
    KeySpec
    -0.68
     invokingState
    -0.67
    ArgsConstructor
    -0.65
     محفوظة
    -0.64
    __(/*!
    -0.60
    migrationBuilder
    -0.59
    nologue
    -0.59
    POSITIVE LOGITS
    {}".
    0.50
     amitié
    0.50
     royaume
    0.49
    "]),
    0.49
    ној
    0.49
    لاعات
    0.48
     dynamical
    0.48
    IUrlHelper
    0.48
    }");
    0.47
     sandalias
    0.47
    Activations Density 0.028%

    No Known Activations