© 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. 5-CLT-HP
    7. 93993
    Prev
    Next
    INDEX
    Explanations

    removed

    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
     remaining
    -0.50
     residual
    -0.48
     removal
    -0.45
     freed
    -0.43
    Left
    -0.43
     néglig
    -0.43
    êmes
    -0.43
     polaire
    -0.43
     left
    -0.42
     остав
    -0.42
    POSITIVE LOGITS
    DebuggerNonUser
    0.83
    TintMode
    0.71
    Tikang
    0.71
     FetchType
    0.71
     ujednoznacz
    0.69
    SpringRunner
    0.67
     '\\;'
    0.67
    AutoField
    0.66
    ########.
    0.65
    yntaxException
    0.65
    Activations Density 0.002%

    No Known Activations