© 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. 0-CLT-HP
    7. 97746
    Prev
    Next
    INDEX
    Explanations

    Indicating (technical/scientific context)

    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
     indicate
    -1.30
     indicates
    -1.30
     indicating
    -1.24
     Indicates
    -1.12
    indicates
    -1.07
    indicate
    -1.01
     indicated
    -0.99
    Indicates
    -0.96
     indicar
    -0.88
     Indicate
    -0.84
    POSITIVE LOGITS
     lateinit
    0.59
    AccessorTable
    0.59
     通販
    0.58
    tahui
    0.57
    ագրություններ
    0.56
    SourceChecksum
    0.54
    ]<<"
    0.52
    SBATCH
    0.51
    ]};
    0.51
     esteve
    0.51
    Activations Density 0.081%

    No Known Activations