© 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. 18494
    Prev
    Next
    INDEX
    Explanations

    phrases indicating agreement or consistency in observations and results

    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
    MergeFrom
    -0.69
     AssemblyCulture
    -0.67
     '\\;'
    -0.66
    الحياه
    -0.65
     caña
    -0.64
    SPATH
    -0.63
    //
    -0.63
    }],
    -0.63
    }]
    -0.62
     épu
    -0.60
    POSITIVE LOGITS
     continúas
    0.60
    исленность
    0.60
     aug
    0.58
    Искәрмәләр
    0.57
     wireType
    0.54
    TextFormField
    0.53
     PLWABN
    0.51
    vertx
    0.51
     Parcelable
    0.51
    PullParser
    0.51
    Activations Density 0.018%

    No Known Activations