© 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. 3-RES-MATRYOSHKA-DC
    7. 2148
    Prev
    Next
    INDEX
    Explanations

    the word 'sign'

    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
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsigned
    -1.15
     Signed
    -1.10
     signatures
    -1.10
     Signatures
    -1.07
     signature
    -1.06
    Unsigned
    -0.99
    signed
    -0.98
     signed
    -0.98
    unsigned
    -0.97
     Signature
    -0.95
    POSITIVE LOGITS
     sign
    1.84
    Sign
    1.66
     Sign
    1.66
    sign
    1.60
     signs
    1.21
     Signs
    1.05
    Signs
    1.02
    signs
    0.94
    SIGN
    0.94
     Zeichen
    0.90
    Activations Density 0.014%

    No Known Activations