© 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. 5-CLT-HP
    7. 4995
    Prev
    Next
    INDEX
    Explanations

    News articles

    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
    毎
    -0.47
     تضيفلها
    -0.44
     دائ
    -0.44
     occasional
    -0.42
    存于互联网档案馆
    -0.41
    ỗi
    -0.40
     perpetually
    -0.39
     Stamm
    -0.39
     regularly
    -0.39
     serve
    -0.38
    POSITIVE LOGITS
     nakalista
    0.88
     صوتيه
    0.81
     <=",
    0.80
    UnusedPrivate
    0.80
    AntiForgeryToken
    0.80
     AssemblyTitle
    0.77
     виправивши
    0.76
    ########.
    0.75
    protoc
    0.74
    adpleegd
    0.73
    Activations Density 0.040%

    No Known Activations