© 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. 18-RES-MATRYOSHKA-DC
    7. 1454
    Prev
    Next
    INDEX
    Explanations

    the word "Plan" or "Pla" followed by one or two characters (often ar or n or ed).

    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
    Negative Logits
    EDEFAULT
    -1.08
     مشين
    -0.98
    UnusedPrivate
    -0.81
    WebVitals
    -0.79
    gnore
    -0.75
     Himo
    -0.74
    TestingModule
    -0.74
    StructEnd
    -0.73
    Cyfeiriadau
    -0.73
    قایناق‌لار
    -0.72
    POSITIVE LOGITS
     plans
    0.77
     Pla
    0.77
     PLAN
    0.72
     Plans
    0.72
     Pl
    0.72
     PL
    0.67
    Pla
    0.66
     pl
    0.65
    Plans
    0.65
    Pl
    0.63
    Activations Density 0.765%

    No Known Activations