© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-CLT-HP
    7. 704
    Prev
    Next
    INDEX
    Explanations

    Ann

    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
    UnsafeEnabled
    -0.64
    suites
    -0.57
    Predecesor
    -0.53
    Witness
    -0.52
    SOUNDBITE
    -0.52
    dịch
    -0.52
     prefect
    -0.51
    Sabes
    -0.51
     SUITE
    -0.50
    oplayer
    -0.50
    POSITIVE LOGITS
     CreateTagHelper
    0.72
    Personensuche
    0.69
    SizeMode
    0.57
    WarningLevel
    0.57
    ArgsConstructor
    0.55
    Parcelize
    0.54
    AutoField
    0.53
    UpInside
    0.52
    DebuggerNonUser
    0.52
    >>()
    0.51
    Activations Density 0.006%

    No Known Activations