© 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. 19407
    Prev
    Next
    INDEX
    Explanations

    elements related to data representation or variables in scientific contexts

    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
    Vidite
    -0.76
    ("")]
    -0.72
    ($__
    -0.69
     للمعارف
    -0.68
    [][
    -0.66
    MessageOf
    -0.66
     {}),
    -0.65
    يكب
    -0.65
    })->
    -0.65
    TypedDataSet
    -0.64
    POSITIVE LOGITS
    UnsafeEnabled
    0.57
     بيها
    0.45
     knji
    0.44
     tasche
    0.43
    </em>
    0.43
     importancia
    0.42
    HomeAsUp
    0.42
    ScopeManager
    0.42
     lahat
    0.40
    writeField
    0.40
    Activations Density 0.002%

    No Known Activations