Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 5-CLT-HP
    4. 95935
    Prev
    Next
    INDEX
    Explanations

    change

    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
    antMatchers
    -0.57
     Cool
    -0.57
    Hozzáférés
    -0.56
    SourceChecksum
    -0.56
     newData
    -0.53
    onaceous
    -0.53
    BufferException
    -0.52
    RenderAtEndOf
    -0.52
     Capital
    -0.52
     ]
    
    -0.52
    POSITIVE LOGITS
    .
    0.61
     sementara
    0.51
    ,
    0.50
     जबकि
    0.49
     significantly
    0.48
    MigrationBuilder
    0.48
     substantially
    0.47
     století
    0.46
     while
    0.45
    EnableWeb
    0.45
    Activations Density 0.001%

    No Known Activations