© 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. 12-RES-MATRYOSHKA-DC
    7. 15460
    Prev
    Next
    INDEX
    Explanations

    nouns and proper names related to organizations, locations, and significant entities

    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
     Two
    -0.47
    Two
    -0.46
    ResumeLayout
    -0.45
     viso
    -0.44
     karena
    -0.43
     recul
    -0.43
     pecho
    -0.42
     nač
    -0.41
    cer
    -0.41
     مع
    -0.41
    POSITIVE LOGITS
     '\\;'
    1.07
     resourceCulture
    0.95
    __':
    0.92
    __':
    0.92
    verwijspagina
    0.89
    __":
    0.89
     صوتيه
    0.88
     nahilalakip
    0.87
    __":
    0.82
     للمعارف
    0.82
    Activations Density 0.298%

    No Known Activations