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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 93248
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    -1.06
    5
    -0.90
    2
    -0.84
    6
    -0.83
    8
    -0.82
    4
    -0.82
    7
    -0.81
    1
    -0.80
    3
    -0.79
    9
    -0.75
    POSITIVE LOGITS
     للمعارف
    0.57
    APOLIS
    0.55
    BeginContext
    0.55
    ]**
    0.53
    RegistryLite
    0.51
     المعيارى
    0.51
    })`
    0.50
     OMITBAD
    0.49
    ումներ
    0.49
    󠁿
    0.48
    Activations Density 0.009%

    No Known Activations