© 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. 17479
    Prev
    Next
    INDEX
    Explanations

    components of growth media used in bacterial cultures

    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
    ientôt
    -0.78
     للمعارف
    -0.75
     שוליים
    -0.72
    PreferredItem
    -0.71
    цездатний
    -0.67
    NUMX
    -0.66
    évaluateur
    -0.66
    حوالہ
    -0.65
     itſelf
    -0.65
    AsUp
    -0.64
    POSITIVE LOGITS
    MessageDigest
    0.54
    ="@+
    0.46
     Wort
    0.46
    permum
    0.46
    dze
    0.45
    ene
    0.45
    quares
    0.44
     Kons
    0.44
    dig
    0.44
    Manbalar
    0.44
    Activations Density 0.014%

    No Known Activations