© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 96181
    Prev
    Next
    INDEX
    Explanations

    Filepaths and coding

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.69
     betweenstory
    -0.69
    发表于
    -0.67
    AccessorTable
    -0.66
     Efq
    -0.61
     iprot
    -0.61
    oa̍t
    -0.61
    MMV
    -0.59
    ULTURA
    -0.59
    ANTLR
    -0.58
    POSITIVE LOGITS
    DispatchToProps
    0.47
     auto
    0.44
    PHYS
    0.44
    fährt
    0.42
    console
    0.42
    setAdapter
    0.41
    '],$
    0.41
    מע
    0.40
     αυτο
    0.40
    mot
    0.40
    Activations Density 0.000%

    No Known Activations