© 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. 2145
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the phrase "have to" in various contexts

    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
     want
    -0.91
    want
    -0.89
     Want
    -0.88
     NEED
    -0.87
     WANT
    -0.85
     need
    -0.81
    NEED
    -0.75
     Need
    -0.75
     CFP
    -0.71
    Want
    -0.71
    POSITIVE LOGITS
    Carr
    0.84
    Cartney
    0.79
     Pompey
    0.76
    thâu
    0.75
     Lehman
    0.73
    Factory
    0.71
    Gotta
    0.71
    gwick
    0.69
     tramway
    0.69
    *>(
    0.68
    Activations Density 0.047%

    No Known Activations