© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 15282
    Prev
    Next
    INDEX
    Explanations

    inquiries about user security and privacy concerns regarding technology

    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
    SpringRunner
    -0.65
     myſelf
    -0.56
     becauſe
    -0.54
    <bos>
    -0.53
    DllImport
    -0.51
     itſelf
    -0.49
    Personendaten
    -0.48
     theſe
    -0.48
    Niels
    -0.46
     Hallo
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.61
    astéroïdes
    0.61
    tagext
    0.56
    tagHelperRunner
    0.55
    ρου
    0.54
    peq
    0.53
    CodedInputStream
    0.52
     conversations
    0.52
    comuna
    0.52
    adă
    0.52
    Activations Density 0.012%

    No Known Activations