© 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. 18-RES-MATRYOSHKA-DC
    7. 255
    Prev
    Next
    INDEX
    Explanations

    equals signs and nearby symbols

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     ustedes
    -0.63
     ſeveral
    -0.58
     jeunesse
    -0.57
     vocês
    -0.55
     """
    -0.52
    nitř
    -0.50
    دیگر
    -0.49
     hundred
    -0.49
    stateProvider
    -0.49
    böz
    -0.49
    POSITIVE LOGITS
    /=
    1.35
    >=</
    1.13
     CreateTagHelper
    1.03
     $=\
    0.94
    .=
    0.92
     =
    0.85
    _=
    0.85
    ))=\
    0.85
    }=\
    0.85
    :=
    0.83
    Activations Density 1.576%

    No Known Activations