© 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. 3055
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate necessity or requirements

    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
     purpoſe
    -0.73
     Monfieur
    -0.71
     biss
    -0.71
     esenciales
    -0.69
    gamesh
    -0.66
     Agamemnon
    -0.66
     essenziale
    -0.66
    NECT
    -0.63
     Shakspeare
    -0.63
     iParam
    -0.62
    POSITIVE LOGITS
    GLFW
    0.66
    ControllerTest
    0.59
    iempos
    0.59
    RTEE
    0.58
    }],
    0.57
    Requires
    0.56
    requires
    0.56
    rahat
    0.56
    unnitel
    0.56
     requiring
    0.55
    Activations Density 0.114%

    No Known Activations