© 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. 4945
    Prev
    Next
    INDEX
    Explanations

    Item, XML

    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
    NameInMap
    -0.59
    Tembelea
    -0.58
    enumii
    -0.52
    enumi
    -0.52
     հղումներ
    -0.50
     typelib
    -0.50
    labus
    -0.50
    ImageContext
    -0.49
     Италијани
    -0.49
    illigen
    -0.49
    POSITIVE LOGITS
     Wul
    0.52
    #+#
    0.52
     Rel
    0.49
     gynhyrchwyd
    0.49
    ]!='
    0.48
    WillAppear
    0.48
    ->___
    0.47
    Географиясе
    0.46
    GOTO
    0.46
    telo
    0.46
    Activations Density 0.005%

    No Known Activations