© 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. 1-CLT-HP
    7. 46287
    Prev
    Next
    INDEX
    Explanations

    science

    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
    MessageTagHelper
    -0.68
    %)$
    -0.65
     يتيمه
    -0.63
    hoeddwyd
    -0.60
    WriteBarrier
    -0.59
     isInitialized
    -0.59
    WaitGroup
    -0.58
    brainly
    -0.57
    цездатний
    -0.56
    Enllaces
    -0.56
    POSITIVE LOGITS
    ization
    0.66
    ed
    0.58
    ism
    0.58
    ized
    0.58
    Portale
    0.53
    isation
    0.51
    ding
    0.50
     PLWABN
    0.48
    izing
    0.48
    opathic
    0.47
    Activations Density 0.066%

    No Known Activations