© 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
    2. Gemma-2-2B
    3. 20-CLT-HP
    4. 74990
    Prev
    Next
    INDEX
    Explanations

    and

    np_max-act-logits · 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
     NavController
    -0.59
     sessionFactory
    -0.57
     Theſe
    -0.56
    })();
    
    -0.54
     Ode
    -0.53
    __))
    -0.52
     Reagent
    -0.51
    keye
    -0.51
    VolleyError
    -0.50
     softmax
    -0.49
    POSITIVE LOGITS
     farm
    0.67
     her
    0.65
     ranch
    0.61
    fjspx
    0.60
    ranch
    0.59
     Ranch
    0.58
     cro
    0.56
     Signalez
    0.55
     ranchers
    0.55
    GEBURTSDATUM
    0.55
    Activations Density 0.000%

    No Known Activations