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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 12-RES-MATRYOSHKA-DC
    4. 19849
    Prev
    Next
    INDEX
    Explanations

    instances of misrepresentation or misunderstanding of facts and statements

    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
     Ather
    -0.56
    Ers
    -0.53
    rouvez
    -0.53
    \"]
    -0.52
    unay
    -0.51
    ChildScrollView
    -0.51
     tph
    -0.51
    )');
    -0.50
    CloseOperation
    -0.49
     אלא
    -0.49
    POSITIVE LOGITS
     ExecuteAsync
    0.79
    DockStyle
    0.67
    rungsseite
    0.65
    ValueStyle
    0.65
     насељу
    0.61
     misinterpreted
    0.60
    XmlAccessType
    0.58
    Tikang
    0.57
     giuri
    0.57
     Wicidata
    0.56
    Activations Density 0.049%

    No Known Activations