© 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. 92366
    Prev
    Next
    INDEX
    Explanations

    )

    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
    @[+][
    -0.88
    сылкі
    -0.81
    enderror
    -0.78
     itſelf
    -0.78
     noDo
    -0.75
    })));
    -0.75
     gynhyrchwyd
    -0.75
     AssemblyTitle
    -0.75
    tvguidetime
    -0.74
     Administrativna
    -0.73
    POSITIVE LOGITS
     society
    0.50
    ,
    0.48
     lifestyle
    0.47
     community
    0.44
     nation
    0.41
     points
    0.40
     &
    0.40
     economy
    0.39
     and
    0.38
     global
    0.38
    Activations Density 0.002%

    No Known Activations