© 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. 22608
    Prev
    Next
    INDEX
    Explanations

    phrases related to singular entities and cohesion in processes

    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
     Reſ
    -0.85
     itſelf
    -0.85
     Monfieur
    -0.81
     ſtre
    -0.79
     ſche
    -0.76
     الحره
    -0.75
     Anſ
    -0.75
     greateſt
    -0.72
     Conſ
    -0.72
     raiſ
    -0.71
    POSITIVE LOGITS
     vice
    0.54
     gynhyrchwyd
    0.53
    ENDIF
    0.47
    WriteBarrier
    0.47
    żu
    0.46
    publicain
    0.44
    inheit
    0.44
    BEAR
    0.43
    }>
    0.43
    }(),
    0.43
    Activations Density 0.024%

    No Known Activations