© 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. 24-RES-MATRYOSHKA-DC
    7. 1153
    Prev
    Next
    INDEX
    Explanations

    code and configuration file related syntax like equal signs, colons, numbers and tags

    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.24.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.24.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
    UnusedPrivate
    -0.63
     AssemblyVersion
    -0.54
    ลัง
    -0.52
    धिक
    -0.50
    áctenos
    -0.50
    ष्ठ
    -0.49
     Affecting
    -0.49
     Six
    -0.49
    hdc
    -0.49
     Branche
    -0.49
    POSITIVE LOGITS
    0.84
    0.59
    たん
    0.49
    0.49
    ConstraintMaker
    0.48
    protoimpl
    0.48
    tonsoft
    0.46
    AddHtmlAttribute
    0.45
     مث
    0.45
    ṳ
    0.45
    Activations Density 0.086%

    No Known Activations