© 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. 94981
    Prev
    Next
    INDEX
    Explanations

    Spelling and variations

    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
     belang
    -0.46
    beo
    -0.46
     out
    -0.45
    ]")]
    -0.45
    ganza
    -0.45
     Cu
    -0.43
    احب
    -0.43
     Strom
    -0.43
    agers
    -0.41
     Block
    -0.41
    POSITIVE LOGITS
    دانشنامهٔ
    0.65
    EndInit
    0.62
    GoogleApiClient
    0.58
    Lähteet
    0.58
    ثيق
    0.57
    libft
    0.57
     Roskov
    0.57
    ########.
    0.55
    ỡng
    0.55
     protoimpl
    0.55
    Activations Density 0.000%

    No Known Activations