© 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. 5-CLT-HP
    7. 91404
    Prev
    Next
    INDEX
    Explanations

    gases

    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
    aulted
    -0.44
    AsUp
    -0.44
     problems
    -0.44
     eff
    -0.43
     domo
    -0.43
     issues
    -0.42
     AssemblyCulture
    -0.42
     failings
    -0.42
    oked
    -0.42
    CrossRef
    -0.42
    POSITIVE LOGITS
     يتيمه
    0.75
    createStatement
    0.67
    ValueStyle
    0.67
    Personendaten
    0.67
    DockStyle
    0.61
     mergeFrom
    0.61
    @[+][
    0.60
    DebuggerNonUser
    0.60
    RegistryLite
    0.59
    RTDA
    0.58
    Activations Density 0.000%

    No Known Activations