© 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. 92759
    Prev
    Next
    INDEX
    Explanations

    laws

    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
    }]
    -0.51
     محفوظة
    -0.47
    ventus
    -0.47
    InvalidProtocol
    -0.45
    νού
    -0.44
    MockMvc
    -0.44
     Seitz
    -0.44
     Preference
    -0.43
    aui
    -0.42
    ierr
    -0.42
    POSITIVE LOGITS
     EconPapers
    0.96
    
    0.79
    ftagPool
    0.66
     saites
    0.63
     allows
    0.61
     seeks
    0.59
    тельстве
    0.58
    ISupport
    0.58
     exists
    0.58
     says
    0.56
    Activations Density 0.001%

    No Known Activations