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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11562
    Prev
    Next
    INDEX
    Explanations

    URLs or web addresses with varying depth or levels

    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
    Personendaten
    -0.84
     Shakspeare
    -0.79
    DebuggerNonUser
    -0.78
     Chrift
    -0.77
    UnknownFieldSet
    -0.75
     CreateTagHelper
    -0.75
    COUVER
    -0.73
     Majefty
    -0.73
    AndroidJUnit
    -0.72
     prefent
    -0.72
    POSITIVE LOGITS
    ur
    0.42
    &
    0.40
    fur
    0.39
    Dok
    0.38
    蚪
    0.38
    Cllr
    0.37
    Š
    0.37
     &
    0.36
     papan
    0.36
    CDATA
    0.36
    Activations Density 0.006%

    No Known Activations