Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12239
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and equations related to physics

    oai_token-act-pair · gemini-2.0-flash

    equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/width_16k
    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
     فريبيس
    -1.20
     disambiguazione
    -1.08
    +#+#
    -0.98
    QMetaType
    -0.98
     snippetHide
    -0.98
     <=",
    -0.98
     الرياضيه
    -0.94
    AndEndTag
    -0.93
    SourceChecksum
    -0.93
    CppCodeGen
    -0.92
    POSITIVE LOGITS
    anit
    0.28
     virke
    0.28
     agencia
    0.25
    lakukan
    0.24
     porté
    0.24
     magát
    0.24
    ख
    0.22
    烂
    0.22
    提供的
    0.22
     P
    0.22
    Activations Density 5.506%

    No Known Activations