© 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. 1062
    Prev
    Next
    INDEX
    Explanations

    approval

    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
    DoubleQuotes
    -0.68
     ISNI
    -0.60
     Catawiki
    -0.59
    adaptiveStyles
    -0.58
     AttributeSet
    -0.58
    ArrowToggle
    -0.56
    ArgsConstructor
    -0.54
    ]++;
    -0.53
    PreferredItem
    -0.52
    verwijspagina
    -0.52
    POSITIVE LOGITS
    IUrlHelper
    0.51
     a
    0.48
     Einfach
    0.44
     FetchType
    0.44
     restTemplate
    0.44
    PRWEB
    0.43
     past
    0.43
    EndInit
    0.43
     local
    0.43
     former
    0.43
    Activations Density 0.028%

    No Known Activations