© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 12598
    Prev
    Next
    INDEX
    Explanations

    instances of numeric values and related keywords pertaining to programming or coding 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
    Negative Logits
     спо
    -0.47
    ils
    -0.46
    LEN
    -0.45
    اط
    -0.44
    INER
    -0.43
    iner
    -0.43
     запа
    -0.43
    <u>
    -0.42
    len
    -0.42
    aw
    -0.41
    POSITIVE LOGITS
    __':
    1.05
    __":
    1.05
     المعيارى
    0.87
    :+:
    0.85
    HttpPut
    0.85
    StructEnd
    0.81
    __":
    0.81
     resourceCulture
    0.81
    ]")]
    0.79
    TemporalType
    0.78
    Activations Density 0.001%

    No Known Activations