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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-RES-MATRYOSHKA-DC
    4. 15462
    Prev
    Next
    INDEX
    Explanations

    grid-like patterns of structural or visual elements

    oai_token-act-pair · gpt-4.1-nano
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lső
    -0.50
    Gambas
    -0.50
    ntö
    -0.49
    asaran
    -0.46
     صوتيه
    -0.46
    ぜん
    -0.43
     manifiesto
    -0.43
    : 
    -0.42
    ,&
    -0.42
    vábbi
    -0.41
    POSITIVE LOGITS
    '},
    
    0.68
    yntaxException
    0.68
    ]));
    
    0.67
    )]);
    0.66
    '),
    
    0.65
    TintMode
    0.64
    ########.
    0.64
    AutoresizingMask
    0.64
    '}),
    0.63
    Rohy
    0.63
    Activations Density 0.198%

    No Known Activations