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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-CLT-HP
    7. 97379
    Prev
    Next
    INDEX
    Explanations

    scientific/technical texts

    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
     transi
    -0.75
     SafeMath
    -0.65
     useAuth
    -0.64
    FailureListener
    -0.62
    Buildable
    -0.60
    tagext
    -0.56
    imanapun
    -0.54
    XmlAccessorType
    -0.54
    +#+#
    -0.54
    inescence
    -0.53
    POSITIVE LOGITS
     tongues
    0.49
    +#+
    0.48
     صوتيه
    0.46
    re
    0.43
    "}")
    0.42
    __":
    0.41
    morris
    0.41
     وتسجيلات
    0.41
    rer
    0.41
    story
    0.40
    Activations Density 0.062%

    No Known Activations