© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-CLT-HP
    7. 74641
    Prev
    Next
    INDEX
    Explanations

    be

    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
     semula
    -0.59
    antaranya
    -0.49
     dipin
    -0.47
    робнее
    -0.47
     antaranya
    -0.44
     testigos
    -0.44
     begitu
    -0.44
    Displayed
    -0.44
     käytet
    -0.42
     valmis
    -0.42
    POSITIVE LOGITS
     electrification
    0.83
     evaporation
    0.82
     dehydration
    0.81
     phosphorylation
    0.79
     suspension
    0.79
     vorticity
    0.77
     hydration
    0.77
     الحره
    0.77
     fibrillation
    0.77
     pollination
    0.76
    Activations Density 0.014%

    No Known Activations