© 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. 15459
    Prev
    Next
    INDEX
    Explanations

    currency symbols and values

    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
    المراجع
    -0.49
     thị
    -0.47
    simpleType
    -0.46
    atk
    -0.44
    ons
    -0.44
     oprot
    -0.44
    ANSA
    -0.44
    /******/
    -0.43
     toJson
    -0.42
     Augenblick
    -0.41
    POSITIVE LOGITS
     وتسجيلات
    0.82
    SupportActionBar
    0.70
    )))));
    0.70
    الدراسه
    0.70
    };*/
    0.69
    ])));
    0.66
     cdti
    0.65
    XmlAccessType
    0.65
     hâte
    0.64
    ως
    0.64
    Activations Density 0.001%

    No Known Activations