© 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
    3. Gemma-2-2B
    5. 1-CLT-HP
    7. 880
    Prev
    Next
    INDEX
    Explanations

    we

    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
     AssemblyProduct
    -0.69
     الحره
    -0.63
    ContentAsync
    -0.62
    parsedMessage
    -0.61
    DebuggerNonUser
    -0.59
     propOrder
    -0.57
    $_['
    -0.54
    Geplaatst
    -0.54
     iprot
    -0.54
     createSlice
    -0.54
    POSITIVE LOGITS
    ]--;
    0.57
    /**
    0.51
     juges
    0.48
     作者
    0.46
    ]++;
    0.46
    ällor
    0.46
    }>{
    0.45
     mères
    0.45
    COUVER
    0.45
     solares
    0.45
    Activations Density 0.004%

    No Known Activations