© 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. 3201
    Prev
    Next
    INDEX
    Explanations

    definitions and descriptions of falsehoods or deceit

    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
    :+:
    -0.71
    GGLE
    -0.54
     genio
    -0.52
    blå
    -0.51
     اع
    -0.51
     tic
    -0.49
     Cumming
    -0.48
    })}\
    -0.48
     veritable
    -0.47
     interplay
    -0.47
    POSITIVE LOGITS
    RunWith
    0.72
    XmlAccessType
    0.67
    下载附件
    0.58
     doInBackground
    0.57
    OGND
    0.57
     especially
    0.56
    gorm
    0.56
    ScopeManager
    0.56
    orghini
    0.55
    +:+
    0.54
    Activations Density 0.430%

    No Known Activations