© 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. 1-CLT-HP
    7. 45779
    Prev
    Next
    INDEX
    Explanations

    with

    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
     EconPapers
    -1.01
    OGND
    -0.93
    KommentareTeilen
    -0.88
     nakalista
    -0.86
    contentLoaded
    -0.86
    +#+#
    -0.85
    StructEnd
    -0.84
    новниш
    -0.82
    ]")]
    -0.81
     snippetHide
    -0.80
    POSITIVE LOGITS
     of
    0.52
     providing
    0.50
     eliminating
    0.46
     combining
    0.46
     being
    0.45
     not
    0.44
     creating
    0.43
    готовление
    0.43
    ParallelGroup
    0.43
     as
    0.42
    Activations Density 0.060%

    No Known Activations