© 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. 18-RES-MATRYOSHKA-DC
    7. 265
    Prev
    Next
    INDEX
    Explanations

    words related to how well a model or method performs or its reliability

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
    WithFormat
    -0.60
    ings
    -0.53
     LUMP
    -0.51
    RegistryLite
    -0.50
    <code>
    -0.49
    meneu
    -0.49
    :✨
    -0.48
    式
    -0.45
    N
    -0.45
     kasarigan
    -0.45
    POSITIVE LOGITS
    fulness
    0.74
    issues
    0.73
    CardNumber
    0.71
     saites
    0.68
     issues
    0.68
    idance
    0.67
    nicity
    0.66
     بخشی
    0.65
    Enllaços
    0.64
    HasForeignKey
    0.64
    Activations Density 2.046%

    No Known Activations