© 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. 87
    Prev
    Next
    INDEX
    Explanations

    text that is indented at the beginning of a line and is followed by other numbers or dashes in that same line

    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
     she
    -0.44
     or
    -0.41
     but
    -0.41
     m
    -0.40
     X
    -0.40
     k
    -0.40
     same
    -0.40
     y
    -0.39
     way
    -0.39
     Y
    -0.39
    POSITIVE LOGITS
    The
    1.19
    In
    1.00
    This
    0.96
    We
    0.92
    For
    0.91
    There
    0.90
    When
    0.88
    As
    0.88
    It
    0.86
    To
    0.86
    Activations Density 6.917%

    No Known Activations