© 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. 18-RES-MATRYOSHKA-DC
    7. 1103
    Prev
    Next
    INDEX
    Explanations

    square roots

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.18.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.18.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
     far
    -0.60
     body
    -0.56
     pres
    -0.56
    })()
    -0.56
     Bedarf
    -0.55
     den
    -0.51
    اف
    -0.50
     ['$
    -0.50
     M
    -0.50
     cu
    -0.49
    POSITIVE LOGITS
    qrt
    1.31
    sqrt
    1.01
     sqrt
    0.96
    PathParam
    0.82
    ^(@)
    0.81
    featureID
    0.80
    ImageContext
    0.79
     насељу
    0.74
    InputBorder
    0.74
    BagLayout
    0.73
    Activations Density 0.201%

    No Known Activations