© 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. 24225
    Prev
    Next
    INDEX
    Explanations

    references to hills or the term "Hill."

    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
    ropical
    -0.85
    bekah
    -0.85
     Knockout
    -0.84
    "],
    -0.75
     Tad
    -0.75
    いる
    -0.74
    `]
    -0.71
    feras
    -0.70
    quard
    -0.69
    gnac
    -0.69
    POSITIVE LOGITS
     Hill
    1.85
    Hill
    1.77
     hill
    1.73
     hills
    1.68
     HILL
    1.61
    hill
    1.48
     Hills
    1.46
    Hills
    1.34
    HILL
    1.27
    hills
    1.20
    Activations Density 0.008%

    No Known Activations