© 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. 5257
    Prev
    Next
    INDEX
    Explanations

    Proper nouns and adjectives

    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
    ,
    -0.66
     and
    -0.61
     in
    -0.59
    o
    -0.58
     дописавши
    -0.56
    abel
    -0.56
     of
    -0.55
    ;
    -0.55
     sal
    -0.54
    .
    -0.54
    POSITIVE LOGITS
     varandra
    0.55
     stället
    0.54
     GenerationType
    0.54
     wikipagina
    0.53
     feroit
    0.50
     senare
    0.50
    hamdu
    0.50
     zelve
    0.50
    ++
    0.50
    ----------
    0.49
    Activations Density 0.017%

    No Known Activations