© 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. 25760
    Prev
    Next
    INDEX
    Explanations

    sections or headings that summarize the outcomes of analyses

    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
    excellents
    -0.42
    segu
    -0.41
    nologia
    -0.41
    ∮
    -0.41
    ochemical
    -0.40
     صلاح
    -0.40
     Bottom
    -0.40
    endish
    -0.39
     общем
    -0.39
     Tag
    -0.39
    POSITIVE LOGITS
    Datuak
    1.02
    PerformLayout
    0.97
    KommentareTeilen
    0.88
     незавершена
    0.87
     AssemblyCulture
    0.79
    LookAnd
    0.79
     MessageBoxIcon
    0.76
    ScopeManager
    0.75
    netbeans
    0.75
    tagHelperRunner
    0.74
    Activations Density 0.008%

    No Known Activations