© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 4063
    Prev
    Next
    INDEX
    Explanations

    academic 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
    IContainer
    -0.49
    Alike
    -0.49
    UMBIA
    -0.45
     value
    -0.44
    为止
    -0.43
    ]._
    -0.43
     left
    -0.43
    ovia
    -0.41
     learn
    -0.41
     leave
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.77
     صوتيه
    0.68
     intptr
    0.68
    GEBURTSDATUM
    0.65
    StoryboardSegue
    0.63
     wikihow
    0.59
    scrapy
    0.59
    efty
    0.59
     disambiguazione
    0.58
    -------
    0.55
    Activations Density 0.000%

    No Known Activations