© 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
    2. Gemma-2-2B
    3. 1-CLT-HP
    4. 13090
    Prev
    Next
    INDEX
    Explanations

    methods and efficacy

    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
     InputDecoration
    -0.58
     fit
    -0.52
    koon
    -0.46
    XtraReports
    -0.45
     häls
    -0.45
     kaca
    -0.45
     health
    -0.44
     skolan
    -0.44
     mī
    -0.44
     iklan
    -0.43
    POSITIVE LOGITS
     متعلقه
    0.84
    SourceChecksum
    0.84
     >=",
    0.72
    WriteTagHelper
    0.71
    ThroughAttribute
    0.69
    #+#
    0.67
    __*/
    0.63
    GenerationType
    0.63
     tfsi
    0.62
     burnt
    0.61
    Activations Density 0.004%

    No Known Activations