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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 5-CLT-HP
    7. 1978
    Prev
    Next
    INDEX
    Explanations

    dark

    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
     resourceCulture
    -0.49
     BrowserModule
    -0.44
    STIC
    -0.42
     surla
    -0.40
     opportune
    -0.39
    ]]
    -0.39
    ParseTree
    -0.39
    ])));
    -0.39
    entista
    -0.39
    })$}
    -0.38
    POSITIVE LOGITS
    InputTagHelper
    0.67
     '{@
    0.65
    Vidite
    0.57
    Personensuche
    0.56
     validamos
    0.56
     Roskov
    0.55
    !("{
    0.55
    APORE
    0.55
     Chwiliwch
    0.55
    their
    0.54
    Activations Density 0.000%

    No Known Activations