© 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. 4686
    Prev
    Next
    INDEX
    Explanations

    concepts related to interface requirements and performance criteria

    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
     unknownFields
    -0.45
    FullScreen
    -0.41
     maar
    -0.40
     pesar
    -0.40
    is
    -0.39
     ubicada
    -0.39
    um
    -0.37
     _:
    -0.36
    月号
    -0.36
     válvulas
    -0.36
    POSITIVE LOGITS
     препратки
    0.80
     AssemblyCulture
    0.77
     ujednoznacz
    0.75
    tagHelperRunner
    0.74
    argout
    0.73
     برانيه
    0.71
    exitRule
    0.70
    AndEndTag
    0.69
    UnsafeEnabled
    0.69
     AssemblyVersion
    0.68
    Activations Density 0.556%

    No Known Activations