© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 12-RES-MATRYOSHKA-DC
    7. 11384
    Prev
    Next
    INDEX
    Explanations

    terms related to diversity and conservation in various contexts

    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
    fjspx
    -0.43
    zzar
    -0.41
     and
    -0.40
     top
    -0.40
    om
    -0.40
    __/
    -0.40
     even
    -0.40
     poli
    -0.40
    awia
    -0.39
    zz
    -0.39
    POSITIVE LOGITS
     entanto
    0.90
    ########.
    0.85
    SourceChecksum
    0.84
     فريبيس
    0.83
    ftagPool
    0.77
     nahilalakip
    0.75
     όμως
    0.73
     however
    0.73
     autorytatywna
    0.73
     GenerationType
    0.71
    Activations Density 0.876%

    No Known Activations