© 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. 0-CLT-HP
    7. 43849
    Prev
    Next
    INDEX
    Explanations

    code

    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
     <<<<<<<<<<<<<<
    -0.89
     AssemblyTitle
    -0.84
    ContentAsync
    -0.73
    TargetException
    -0.73
     contextLoads
    -0.72
    
    -0.71
     []:
    -0.69
     doInBackground
    -0.67
     فريبيس
    -0.65
    awaiter
    -0.65
    POSITIVE LOGITS
    ranno
    0.49
     voort
    0.49
    ="/">
    0.49
    })).
    0.48
    AutoSize
    0.45
    стях
    0.44
    otten
    0.44
    Życiorys
    0.43
    lasser
    0.43
    ња
    0.42
    Activations Density 1.016%

    No Known Activations