© 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. 3480
    Prev
    Next
    INDEX
    Explanations

    assertions or declarations about the capabilities or characteristics of something

    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
    脚注の使い方
    -1.12
    Datuak
    -0.90
     AssemblyTitle
    -0.89
    зец
    -0.89
    Personendaten
    -0.84
    bewerken
    -0.84
     Monfieur
    -0.82
     笔画
    -0.82
    ArgsConstructor
    -0.81
    ^(@)
    -0.81
    POSITIVE LOGITS
    定
    0.54
     said
    0.53
     saying
    0.50
     believes
    0.47
     пом
    0.44
     knows
    0.44
     decir
    0.44
    直
    0.44
     定
    0.43
     says
    0.41
    Activations Density 0.500%

    No Known Activations