© 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. 5461
    Prev
    Next
    INDEX
    Explanations

    benign

    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
    Поэтому
    -0.57
     noires
    -0.55
     détach
    -0.55
     colorés
    -0.54
    umin
    -0.54
    irchen
    -0.53
    cipit
    -0.52
     africains
    -0.52
    Erreferentziak
    -0.51
    assertNot
    -0.51
    POSITIVE LOGITS
     disambiguazione
    0.59
     VizieR
    0.58
     nahilalakip
    0.55
     సౌకర్య
    0.53
    NavController
    0.51
     ratchet
    0.50
     onPostExecute
    0.50
     ostavi
    0.50
    Cyfeiriadau
    0.49
     resurre
    0.49
    Activations Density 0.000%

    No Known Activations