© 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. 1-CLT-HP
    7. 15055
    Prev
    Next
    INDEX
    Explanations

    soil

    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
    <bos>
    -0.60
    المناصب
    -0.55
    adaptiveStyles
    -0.50
     Paglinawan
    -0.49
     zewnętrzne
    -0.47
    ์ตูน
    -0.46
    osoever
    -0.45
    ‗
    -0.45
     esfuerzos
    -0.45
     DBNull
    -0.45
    POSITIVE LOGITS
    TestingModule
    0.65
    AnchorStyles
    0.63
    ValueGenerated
    0.61
    :✨
    0.59
    ftagPool
    0.51
    MockBean
    0.50
     hamsters
    0.50
     GenerationType
    0.50
     Cid
    0.50
    gister
    0.50
    Activations Density 0.010%

    No Known Activations